📄 arXiv 일일 적재 — 산업 paradigm 시그널
cs.AI · cs.LG · cs.CV · cs.RO · q-bio · physics.optics · econ.GN 등 톱다운 chain 관련. codex 로 chain 매칭·새 paradigm 자동 감지.
🔭 새 패러다임 후보 (20건 — 기존 chain 밖 신호)
Valinor: Architectural Support for Fast, Energy-Efficient and Programmable Physical Memory Allocation
· 2026-07-16 · Architecture
- OS 정책을 실행하는 프로그래머블 메모리 할당 하드웨어
- 서버리스·마이크로서비스의 지연과 에너지 병목 완화
- RISC-V·데이터센터 CPU의 메모리 관리 차별화 신호
Goal-Oriented Semantic Communication for Distributed ISAC-Enabled Vehicle Coordination
· 2026-07-16 · Robotics
- 의미 기반 ISAC로 차량 제어 신호를 선택 전송
- RSU·기지국 협업이 자율교통 인프라 수요 확대
- V2X 통신·엣지 AI·차량용 센싱 장비 수혜
NeuronSoup: Evolving Asynchronous, Shared-Neuron Temporal Graphs without Backpropagation
· 2026-07-16 · cs.NE
- 비동기·공유 뉴런 기반 신경망 구조 제안
- 역전파 없이 유전알고리즘으로 구조·지연 동시 탐색
- 초저용량 엣지 AI·뉴로모픽 하드웨어 수혜 가능
T^2MLR: Transformer with Temporal Middle-Layer Recurrence
· 2026-07-16 · cs.CL
- 중간층 상태를 토큰 간 재활용하는 추론 구조
- 전체 반복보다 일부 층 반복이 효율·성능 우위
- 기존 1.7B 모델 개조 가능해 추론 AI 비용 절감
AutoSynthesis: An agentic system for automated meta-analysis
· 2026-07-16 · AI
- 멀티에이전트가 메타분석 전 과정을 자동화
- 의료·정책 리서치의 검증 비용 절감 가능
- 과학 지식생산용 에이전트 시장 신호
From Pixels to States: Rethinking Interactive World Models as Game Engines
· 2026-07-15 · Vision
- 픽셀 예측형 월드모델을 상태 기반 게임엔진으로 재정의
- 행동·상태·관측 루프가 실시간 생성형 게임 핵심 인프라
- 대규모 상태 정렬 게임 데이터가 AI 게임엔진 경쟁력 좌우
A Self-Evolving Agent for Longitudinal Personal Health Management
· 2026-07-15 · AI
- 개인 건강 AI를 일회성 질의에서 장기 동반자로 전환
- 자기진화 메모리가 정확도·프라이버시를 함께 개선
- 디지털헬스·원격관리·의료 AI 에이전트 수혜 신호
DermDepth: Toward Monocular Metric Scale 3D Reconstruction Models for Dermatology
· 2026-07-14 · Vision
- 단일 피부 이미지로 실측 3D 복원 구현
- 합성 데이터가 임상 계측 정확도 대폭 개선
- 피부암·상처 원격진단 워크플로 고도화 신호
LatentFlow: A General Framework for Conditioning Stochastic Processes
· 2026-07-14 · stat.ML
- 학습 없이 확률과정 조건부 샘플링 통합
- 물리·생명과학 시뮬레이션 추론 비용 절감
- 디지털트윈·과학컴퓨팅 적용 범위 확대
A Shortcut to Statistically Steady-State Turbulence with Flow Matching
· 2026-07-14 · physics.plasm-ph
- 과도상태를 건너뛰는 난류 정상상태 생성
- 5D 자이로키네틱 시뮬레이션 비용 절감
- 핵융합·플라즈마 설계 가속 가능성
Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques
· 2026-07-14 · ML
- 확산형 LLM의 병렬 생성 실용화 가속
- 캐싱·시스템 최적화가 추론비용 좌우
- AI 추론 인프라·서빙 SW 수혜 가능
Reproducible Reservoir Computing with Thermally Driven Superparamagnets: Controlling Temperature Sensitivity
· 2026-07-14 · Emerging Tech
- 초저전력 자성 나노닷 reservoir 컴퓨팅
- 이종 크기 설계로 온도 변화 내성 확보
- 엣지 AI용 비전통 반도체 소자 가능성
Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model
· 2026-07-14 · AI
- 확산형 언어모델로 음성 전사를 병렬 생성
- 고정 26B MoE에 0.16% 어댑터만 학습
- 긴 음성도 8단계 처리, 추론비용 절감 가능
$\mathtt{Q^2SAR}$: overcoming classical bottlenecks in drug discovery via quantum multiple kernel learning
· 2026-07-13 · quant-ph
- 양자 다중커널로 QSAR 예측 정확도 개선
- 신약 후보 선별·독성 예측 비용 절감 가능
- 양자컴퓨팅 성숙 시 AI 신약개발 수혜 확대
CatRetriever: Contrastive Representation Learning for Slab-to-Bulk Retrieval in Generative Catalyst Discovery
· 2026-07-13 · ML
- 촉매 표면 생성물을 벌크 결정으로 연결
- 역설계 촉매의 합성가능성 검증 강화
- 화학·소재 AI 플랫폼 고도화 수혜
Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction
· 2026-07-13 · AI
- LLM 추론을 압축 규칙 상태로 분리하는 아키텍처
- 칩 설계 합성 정확도 31%→58%로 생산성 개선
- 에이전트형 AI의 검증·재생성 인프라 수요 신호
Sharing economy in the era of full automation: Evidence from autonomous vehicle on-demand mobility services
· 2026-07-09 · Economics
- 개인 자율주행차의 유휴시간을 모빌리티 공급으로 전환
- 중앙 배차·동적 가격이 도심과 외곽 서비스 품질을 동시 개선
- 로보택시 플랫폼·차량 운영 SW의 자산공유 수익모델 신호
Anomalous Reflection of Caustic Spin-Wave Beams in a Magnonic Waveguide
· 2026-07-09 · cond-mat.mes-hall
- 비등방 자성체에서 스넬 법칙과 다른 반사 법칙 실증
- 자기장 조절형 마그논 빔 라우팅·조향 가능성 제시
- 저전력 스핀파 기반 RF·신호처리 소자 수혜 기대
Low-latency FPGA-based electronic control system for fast preparation of defect-free atom arrays
· 2026-07-09 · quant-ph
- FPGA로 PC 없는 원자배열 피드백 구현
- 결함 없는 중성원자 배열 성공률 95.4%
- 양자제어 FPGA·PXIe 장비 수요 확대
DrugGen 2: A disease-aware language model for enhancing drug discovery
· 2026-07-09 · Bio·Q
- 질환 온톨로지·표적서열 동시 조건 신약 생성
- GPT-2·GRPO로 결합력·신규성 함께 최적화
- AI 신약설계·CRO·후보물질 검증 수요 확대
🔗 기존 chain 매칭 논문 30건
- cpo-photonics Right Device, Right Place: Variation-Aware Placement and Design Optimization for Robust Photonic Lattice-Filter Demultiplexers 2026-07-16
- ai-substrate PolyQ: Codesigning End-to-End Quantization Framework for Scalable Edge CPU LLM Inference 2026-07-16
- ai-substrate ExaGEMM: Exploration Framework for CPU-Driven ML Inference via Associative In-Register Computing for Low-Bit GEMM 2026-07-16
- ai-substrate CODA: Algorithm-Hardware Co-design for Edge Video Diffusion via NMP-Enabled Compute-Cache Operator Disaggregation 2026-07-16
- ai-substrate NIFA: Nonlinear IMC enhanced FPGA for efficient ML inference 2026-07-16
- ai-substrate Campaign Diagrams: Visualizing the March Through the Phases of a Workload 2026-07-16
- physical-ai-vlm KineFuse: Kinematic-Aware Haptic Fusion for In-Hand Occluded-Object Pose Tracking 2026-07-16
- physical-ai-vlm Towards Human-like Physical Intelligence: LifelongVision-Language-Action Learning for Robotic Manipulation 2026-07-16
- physical-ai-vlm OASIS-Map: Object-Level Change Detection in Multi-Session Mapping using Semantic Correspondence Matching 2026-07-16
- physical-ai-vlm Human-Robot Interaction in GenAI Architectures via the Agent-Client Protocol 2026-07-16
- physical-ai-vlm Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control 2026-07-16
- physical-ai-vlm AeroAct: Action-Centered World-Action Models for Language-Conditioned Quadrotor Flight 2026-07-16
- physical-ai-vlm CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking 2026-07-16
- physical-ai-vlm Risk-Aware Belief Control Barrier Functions over Random Finite Sets 2026-07-16
- physical-ai-vlm Learning Agile Navigation in Crowded Environments for Quadruped Robots 2026-07-16
- physical-ai-vlm SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment 2026-07-16
- physical-ai-vlm DriftWorld: Fast World Modeling through Drifting 2026-07-16
- physical-ai-vlm Catch, Throw, Repeat: Planning for Human-Robot Partner Juggling 2026-07-16
- physical-ai-vlm Assessing Physical Frailty and Fall-Risk Indicators with Social Robots: An in situ Evaluation with Older Adults 2026-07-16
- physical-ai-vlm Scaling Behavior Foundation Model for Humanoid Robots 2026-07-16
- physical-ai-vlm AHEAD: Anticipatory Hand-Driven Teleoperation via Human Intent Prediction 2026-07-16
- physical-ai-vlm Stigmergic Graph Memory: An Environment-Aware Approach for Many-to-Many Multi-Agent Pickup and Delivery 2026-07-16
- physical-ai-vlm MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos 2026-07-16
- physical-ai-vlm ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors 2026-07-16
- physical-ai-vlm HoloGeo: Mitigating Landmark Bias in Geo-localization via Evidence-Driven Reasoning 2026-07-16
- physical-ai-vlm Hierarchical Denoising For Multi-Step Visual Reasoning 2026-07-16
- physical-ai-vlm BadWAM: When World-Action Models Dream Right but Act Wrong 2026-07-16
- physical-ai-vlm Online Neural Space Time Memory for Dynamic Novel View Synthesis 2026-07-16
- physical-ai-vlm Benchmarking Multimodal Large Language Models for Scientific Visualization Literacy 2026-07-16
- physical-ai-vlm Symbal: Detecting Systematic Misalignments in Model-Generated Captions 2026-07-16
Which Green Technology to Subsidize? Evidence from Electric Vehicles in South Korea
We develop a framework to compare the relative effectiveness of subsidizing alternative emission-reducing technologies. We show that an intermediate technology may reduce emissions more effectively than the cleanest technology if it induces sufficiently greater substitution away from the prevailing …
Youngjin Hong, In Kyung Kim, Frank Verboven · 📄 PDF
Governing Artificial Intelligence: Public Preferences and Regulatory Options
Artificial intelligence (AI) is rapidly transforming economies, societies, and polities, raising fundamental questions about how it should be regulated. Policymakers face choices over whether to prioritize innovation or safety, rely on public oversight or private self-regulation, and govern national…
Magnus Lundgren, Jonas Tallberg · 📄 PDF
Does Multi-Agent Debate Improve AI Feedback on Research Papers?
Probably not, at least for meta-analyses in economics. In a pre-registered, identity-masked, within-paper experiment, the authors of 44 meta-analyses ranked three AI reports on their own paper by usefulness for improving it: a single pass by a frontier model against two multi-agent debate tools we b…
Tomas Havranek, Zuzana Irsova · 📄 PDF
Thermodynamic theory of voting and EU elections
We introduce a thermodynamic theory of voting and show that it provides a good description of distribution of party votes in EU elections. The theory traces parallels between system energies of coupled nonlinear oscillators and party vote fractions. Such a classical system evolution is characterized…
Klaus M. Frahm, Dima L. Shepelyansky · 📄 PDF
Platform Choice, Trust, and Privacy in the Consumer AI Assistant Market
We study how a representative sample of United States adult AI-assistant users (n=1,999; June 2026) choose among platforms, allocate tasks across them, evaluate provider trustworthiness, and value data-handling features. Estimates are weighted to the AI-user population using external adoption benchm…
Jennifer Zou · 📄 PDF
Indirect Variational Inference: Applications to Earnings Dynamics
Latent-variable models are central to economics but often entail intractable integration. Variational inference (VI), widely used in machine learning, turns this integration into tractable, differentiable optimization by replacing the likelihood with a variational objective. However, guarantees of r…
Neele Balke, Stephane Bonhomme, Thibaut Lamadon · 📄 PDF
Ultrafast programmable Bragg reflection in photonic integrated circuits
Distributed Bragg reflectors (DBRs) are foundational building blocks of classical and quantum photonic technologies. However, their optical responses are typically fixed upon fabrication, limiting circuit robustness, reconfigurability, and functionality in applications from high-speed communications…
Yunxiang Song, Pawan Ratra, Danxian Liu, Jiayu Yang, Zhongshu Liu, Urban Senica, Salma Mohideen, Mingjie Zhang, Xudong L… · 📄 PDF
Phase coherence control of a programmable high-Tc superconductor created by light
The quest for superconductivity created by light extends for more than half a century, yet direct evidence of a true zero-resistance state -whose macroscopic quantum phase coherence is both created and controlled by light -- has remained elusive. Here we report for the first time on a complex but ro…
Viktoria Yursa, Igor Vaskivskyi, Anze Mraz, Damjan Svetin, Sergej Raznjevic, Vinko Srsan, Saso Sturm, Tomaz Mertelj, Mik… · 📄 PDF
Vortex-Beam Transient Absorption Microspectroscopy Resolves Ultrafast Free-Exciton and Polaron Diffusion in 2D Perovskites
Two-dimensional (2D) Ruddlesden Popper perovskites are promising optoelectronic materials with strongly confined excitonic properties; however, probing their ultrafast carrier transport dynamics, particularly the initial nonequilibrium diffusion regime, remains challenging because conventional trans…
Ju-Young Kim, Anirban Mondal, Gi Rim Han, Kwang Jin Lee, Jong Min Lim, Myeongsam Jen, Minhaeng Cho · 📄 PDF
High-rate continuous-variable quantum key distribution coexisting with Tb/s coherent classical transmission in hollow-core fiber
Quantum key distribution (QKD) can provide secret keys with security rooted in quantum mechanics, but operation alongside high-capacity classical traffic remains limited by the excess-noise budget of weak quantum states in conventional solid-core fiber. Here, we combine ultralow-loss anti-resonant h…
Xitao Ji, Siyu Chen, Peng Li, Mingming Zhang, Yilun Chen, Jun Gao, Rui Lin, Bacco Davide, Siqi Yan, Ming Tang · 📄 PDF
3D scanning microscopy through scattering surfaces using the optical memory effect
Wavefront shaping allows light to be focused through scattering objects. However, the wavefront correction found is only valid in a small region called the isoplanatic patch. Here we present a simple approach to extend this isoplanatic patch by shifting and scaling the corrected wavefront appropriat…
Harish Sasikumar, Gerwin Osnabrugge, Kirsten Gerritsma, Bahareh Mastiani, Ivo M. Vellekoop · 📄 PDF
Local Variance-Based Calibration of Programmable Photonic Interferometer Meshes
Programmable photonic interferometer meshes enable reconfigurable linear optical transformations, but their performance depends critically on accurate calibration of Mach-Zehnder interferometers and phase shifters. Conventional methods often require node isolation, dedicated routing paths, orthogona…
Gökhan Elmas, Igor A. Litvin, Janis Nötzel · 📄 PDF
Motion-Based Beamshape Recovery Enables Precision Nanoparticle Sizing
Label-free all-optical nanosizing approaches based on interferometric or darkfield-imaging infer size, composition, or shape from single-particle scattering signals, but these signals are inseparably coupled to the spatially non-uniform illumination profile of the imaging system. Existing normalisat…
D-Dré K. J. M. J. Braam, Daan Wolters, Matz Liebel · 📄 PDF
Empirical verification of principal mode orthogonality and relative phase calibration in photonic lanterns
Photonic lanterns efficiently map input spatial modes to single-mode outputs for applications like high angular resolution imaging and nulling interferometry. However, manufacturing limits prevent full control over the device's mode transfer matrix at the design stage, making empirical characterisat…
Adam K. Taras, Barnaby R. M. Norris, Christopher Betters, Daniel S. Dahl, Andrew Ross-Adams, Peter G. Tuthill, Jin Wei, … · 📄 PDF
Ultraviolet direct absorption microscopy for single particle protein/nucleic acid quantification
Bio-nanoparticles are pivotal to next generation nanotherapeutics, but providing single-particle biomolecular characterization remains a crucial challenge. Herein we present ultra-violet direct absorption microscopy (UV-DAM) to tackle this challenge. UV-DAM is based on a tailored illumination scheme…
C. J. Richards, D. van de Lockand, D. Wolters, M. Liebel · 📄 PDF
Millimetre-scale spectrographs for next-generation photonic instrumentation
We present a set of ultra-compact spectrographs fabricated using two-photon polymerisation, each under 1 mm in length and printed directly onto an optical fiber. This fully integrated, alignment-free architecture enables extremely low-mass instrumentation with broad potential across astrophotonics, …
Emily Ronson, Robert J. Harris, Ariadna Calcines Rosario, Viktoria Kutnohorsky · 📄 PDF
Non-Hermitian Interaction between Light and Photonic Time Crystal Beyond the Floquet Quasinormal Mode Approximation
We report non-Hermitian mode couplings in a photonic time crystal induced by the light within its momentum bandgap. When the relative phase between the light and the photonic time crystal compensates for the detuning, we observe a periodic suppression of exponentially growing Floquet modes. In contr…
Yuhang Li, Yu Zhuang, Zilong Bao, Jingwen Cui, Junda Wang, Xiulai Xu, Chenjiang Qian · 📄 PDF
Spatially multiplexed concentric discrete optical vortices: Complex topological structures and unconventional rotational dynamics
Precise control over the rotational dynamics of structured lights has become a defining objective in contemporary photonics. It plays a central role in governing the functional distribution of optical energy. Particularly, orbital angular momentum driven intensity rotation and azimuthal energy flow …
Aditya Narayana Jena, Vishwa Pal · 📄 PDF
Hybrid Symmetry Breaking for Chiral Quasi-Bound States in the Continuum
Chiral optical modes provide a fundamental platform for spin selective light matter interactions and underpin emerging applications ranging from chiral emission to polarization-controlled photonic devices. They are typically achieved by tailoring specific structural asymmetries to directly induce ci…
Yongtu Zou, Zhiyao Ma, Guangwei Hu, Haoran Ren, Stefan A. Maier, Changxu Liu · 📄 PDF
Analysis of the Topology of a Plasmonic Target-Skyrmion Texture
Topological concepts are frequently used to describe structured optical fields, including plasmonic near fields. Topological descriptions in terms of skyrmion numbers implicitly assume the compactness of the underlying manifold. Even when skyrmion-like textures appear locally, the compactness is usu…
Alexander Neuhaus, Pascal Dreher, Philipp Gessler, Bettina Frank, Timothy J. Davis, Harald Giessen, Karin Everschor-Sitt… · 📄 PDF
Transformation of vector modes by the Faraday effect in strong magnetic fields
Large Faraday rotations can be generated by circular birefringence of atomic samples in an axial magnetic field in the vicinity of atomic resonance lines. The Faraday angle is a function of the magnetic field strength, the optical density of the atomic sample which may be varied by changing the temp…
Sphinx J. Svensson, Craig J. A. Millar, Danielle Pizzey, Ifan G. Hughes, Sonja Franke-Arnold · 📄 PDF
Amplitude- and frequency-modulated combs from an actively locked metasurface external-cavity laser
Optical frequency combs are key components of several photonics applications including spectroscopy, communications, and ultrafast photonics. A central challenge in frequency-comb photonics is to develop sources whose operating state can be precisely controlled and adapted to different application n…
Marco Raffa, Jordane Bloomfield, Yu Wu, Sadhvikas J. Addamane, Alexander Dikopoltsev, Jérôme Faist, Benjamin S. Williams… · 📄 PDF
Unified framework of optical thermodynamics and optical pressure
Optical thermodynamics is a newly developed framework that applies principles from statistical mechanics to describe the intricate behavior of weakly nonlinear, multimode photonic systems. Utilizing this theory, the collective dynamics of complex optical arrangements can be systematically uncovered …
Nikolaos K. Efremidis, Huizhong Ren, Demetrios N. Christodoulides · 📄 PDF
A re-entrant chip-free-space photonic interface for telecom-to-Rubidium spectroscopy
Photonic integrated circuits (PICs) generate, route, and process light with high efficiency, scalability, and functional density on a single chip. Yet the tightly confined on-chip modes can not easily access or effectively interact with atomic vapors, fluids, gain media, and biological samples. Exis…
Jia-Lin Chen, Ruixin Zhou, Deng-Hong Liu, You-Long Fan, Zhu-Bo Wang, Min Chen, Xiang Fang, Jia-Qi Wang, Zheng-Fu Han, Gu… · 📄 PDF
Detecting clear-air turbulence via beam broadening in a Rayleigh-scattering lidar system
The volume of clear-air turbulence (CAT) in the atmosphere at flight cruising altitudes is increasing rapidly, posing a growing problem for civil aviation and resulting in reduced confidence in aviation safety. There are limited remote detection capabilities for CAT, since clear air produces no meas…
Christopher Miller, Daniel Lum, Brandon Rodenburg, Michael Stenner, Anthony DiCarlo, Bradford Snios, Paul D. Williams · 📄 PDF
Topology-Informed Survival Analysis of Breast Cancer Patients Using the Mapper Algorithm
This study applied a mathematical tool from Topological Data Analysis (TDA), called the Mapper algorithm, to gene expression data from more than 1,000 TCGA-BRCA patients to identify hidden molecular patterns associated with survival. Patients located near high-risk regions of the network showed sign…
Emmanuel Kibisi, Olakunle Abawonse, Donald Woukeng · 📄 PDF
Multimodal Semantic-Aware Contrastive Learning For False Negative Mitigation in 3D Medical Imaging
Multimodal Contrastive Learning (CL) has shown significant performance in aligning representations across various data modalities and improving downstream tasks, especially in healthcare. It works by minimizing the distance between matched (positive) data modalities, while maximizing the distance be…
Sara Ketabi, Matthias W. Wagner, Cynthia Hawkins, Uri Tabori, Birgit Betina Ertl-Wagner, Farzad Khalvati · 📄 PDF
Global drivers and barriers to the public acceptance of autonomous vehicles: Evidence from 17 countries
This study investigated the public acceptance of Society of Automotive Engineers Level 3 conditionally automated cars, which can self-drive under certain specified conditions but require the human driver to remain ready to resume control when requested. Previous Unified Theory of Acceptance and Use …
Antonios Saravanos · 📄 PDF
Physical Reservoir Signal Acquisition for Sub-Nyquist Waveform Reconstruction
Physical reservoir computing has traditionally exploited the dynamics of physical systems for computation, enabling tasks such as inference, classification, and prediction. Here, we introduce a fundamentally different paradigm for exploiting physical reservoirs, termed "reservoir signal acquisition"…
Yuito Ito, Anas Skalli, Tetsuya Asai, Satoshi Sunada · 📄 PDF
Right Device, Right Place: Variation-Aware Placement and Design Optimization for Robust Photonic Lattice-Filter Demultiplexers
We propose a Bayesian co-optimization framework for robust integrated photonic lattice-filter demultiplexers, jointly optimizing device placement and design parameters under fabrication and thermal variations. Results show 75% better spectral matching and 45% lower calibration power.
Zahra Ghanaatian, Edwin K. P. Chong, Mahdi Nikdast · 📄 PDF
Stochastic binary networks with asymmetric and time-delayed interactions
Stochastic binary networks are widely used to describe collective dynamics in complex systems and to perform neuromorphic computation, yet realistic networks often contain both asymmetric interactions and finite signal propagation times that fall outside conventional theories. Here we study stochast…
Hantao Zhang, Sidra Gibeault, Matthew W. Daniels, Philippe Talatchian, Ursula Ebels, Advait Madhavan, Mark D. Stiles · 📄 PDF
PolyQ: Codesigning End-to-End Quantization Framework for Scalable Edge CPU LLM Inference
CPUs are the most universal target for on-device LLM inference, but existing low-bit quantization methods offer either coarse operating points or fine-grained mixed precision that is difficult to execute efficiently on CPUs. We present PolyQ, a CPU-oriented compiler/quantization co-design for activa…
Hyunwoo Oh, Suyeon Jang, Hanning Chen, KyungIn Nam, Sanggeon Yun, Ryozo Masukawa, Mohsen Imani · 📄 PDF
ExaGEMM: Exploration Framework for CPU-Driven ML Inference via Associative In-Register Computing for Low-Bit GEMM
Low-bit GEMM is increasingly central to efficient ML inference, yet very-low-bit execution remains a poor fit for conventional CPUs. Practical deployment spans fragmented regimes-from 1/2/4-bit weights to varying activation precision-whose feasibility, reuse opportunity, and support cost differ unde…
Hyunwoo Oh, Suyeon Jang, Hanning Chen, Sanggeon Yun, Ryozo Masukawa, Mohsen Imani · 📄 PDF
Toward Energy-Efficient and Low-Power Arrhythmia Detection for Wearable Devices
Cardiovascular diseases are the leading cause of death worldwide, and conditions such as arrhythmia often require long-term monitoring for effective detection and diagnosis. However, current wearable monitoring devices are bulky, uncomfortable, and typically rely on clinicians to manually evaluate e…
Floriaan Bulten, Yawar Rasheed, Arlene John, Vincenzo Stoico, Ghayoor Gillani · 📄 PDF
Valinor: Architectural Support for Fast, Energy-Efficient and Programmable Physical Memory Allocation
Physical memory allocation establishes virtual-to-physical mappings on demand. In current systems, each minor page fault traps into the kernel and triggers pipeline flushes, stalls, and a long sequence of allocation steps that can cost tens of thousands of cycles. These overheads are increasingly si…
Konstantinos Kanellopoulos, Spiros Galanopoulos, Konstantinos Sgouras, Vlad-Petru Nitu, Ilias Papalamprou, Andreas Kosma… · 📄 PDF
CODA: Algorithm-Hardware Co-design for Edge Video Diffusion via NMP-Enabled Compute-Cache Operator Disaggregation
Deploying Video Diffusion Models (VDMs) on edge devices is appealing for localized and privacy-preserving generation, but their iterative Transformer-based denoising remains too slow for practical local inference. Cross-Timestep Caching (CTC) has emerged as a promising direction for reducing redunda…
Yuanpeng Zhang, YuXuan Wu, Yitong Xiao, Chenhao Xue, Yi Ren, Cong Li, Yihan Yin, Dimin Niu, Guangyu Sun · 📄 PDF
Differentiable Routability-Driven Package Floorplanning with Pin Assignment
As advanced packaging technology evolves, increasing interconnect density in redistribution layers (RDLs) makes routability critical to package floorplanning. Meanwhile, power integrity requirements often reserve fan-in regions for the power delivery network (PDN), forcing signal nets through fan-ou…
Yiqi Huang, Zepeng Li, Zhen Zhuang, Kehao Chen, Genggeng Liu, Tsung-Yi Ho · 📄 PDF
Pattern-Guided Design Space Exploration for FPGA Accelerator Design
High-level synthesis (HLS) raises the abstraction level of FPGA accelerator design from hardware description languages to C/C++, but high-quality results still depend on schedule decisions such as pipelining, unrolling, tiling, reordering, and buffering. These decisions create a combinatorial design…
Jialiang Zhang, Weiman Yan, Yuelin Zou · 📄 PDF
NIFA: Nonlinear IMC enhanced FPGA for efficient ML inference
Recent FPGAs have improved deep learning (DL) inference efficiency through dedicated tensor blocks and in-BRAM computation. ReRAM-based analog in-memory computing (IMC) pushes efficiency further, offering an order-of-magnitude improvement in compute density and energy efficiency over conventional di…
Jiajun Hu, Ruthwik Reddy Sunketa, Lei Zhao, Archit Gajjar, Luca Buonanno, Aman Arora · 📄 PDF
Campaign Diagrams: Visualizing the March Through the Phases of a Workload
We present campaign diagrams, a visualization technique for phase-level analysis of resource utilization and bottlenecks in modern workloads. Existing tools have a trade-off: rooflines aggregate a workload into a single point and lose all notion of time, while profilers and traces expose fine-graine…
Toluwanimi O. Odemuyiwa, John D. Owens, Michael Pellauer, Joel S. Emer · 📄 PDF
KineFuse: Kinematic-Aware Haptic Fusion for In-Hand Occluded-Object Pose Tracking
Dexterous in-hand manipulation requires continuous 6D pose tracking, yet the manipulating fingers inevitably occlude the object from the camera. We study how to structure the sparse haptic signals already available on multi-fingered hands, including proprioception, proximal force/torque, and binary …
Chanyoung Ahn, Jaesung Lee, Sungwoo Park, Donghyun Hwang · 📄 PDF
Towards Human-like Physical Intelligence: LifelongVision-Language-Action Learning for Robotic Manipulation
Similar to the natural capabilities of humans to sequentially learn new tasks, robots with Vision-Language-Action (VLA) models should possess lifelong learning ability to learn a new task when deployed in open-world environments. However, most recently proposed lifelong learning models aim to effect…
Yao He, Gan Sun, Wenqi Liang, Fazeng Li, Yang Cong · 📄 PDF
Modeling and Validation of Quality of Control for Edge-Offloaded Collaborative Navigation
Collaborative control in complex environments is severely challenged by stochastic wireless delay and reliability variations, which can degrade navigation, tracking, and collision avoidance. These network-induced uncertainties complicate the maintenance of energy efficiency during collaborative task…
Neelabhro Roy, Mikael Hammarling, Victor Nan Fernandez-Ayala, Gourav Prateek Sharma, Mani H. Dhullipalla, Dimos V. Dimar… · 📄 PDF
OASIS-Map: Object-Level Change Detection in Multi-Session Mapping using Semantic Correspondence Matching
Map representations which are consistent across repeated visits to a real-world semi-static environment are very useful for long-term robotic inspection. In such settings, the scene may evolve while the robot is absent, with objects appearing, disappearing, moving, or being replaced, quickly making …
Haedam Oh, Yifu Tao, Nived Chebrolu, Maurice Fallon · 📄 PDF
Human-Robot Interaction in GenAI Architectures via the Agent-Client Protocol
Recent advances in Generative Artificial Intelligence (GenAI), particularly Large Language Models (LLMs), are driving robotic architectures toward agent-based high-level orchestration, in which natural-language instructions can be translated into context-aware action sequences. While the integration…
Jesus Moncada-Ramirez, Jose-Raul Ruiz-Sarmiento, Javier Gonzalez-Jimenez · 📄 PDF
Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control
World Action Models (WAMs) enable semantically- and physically-informed control but are brittle under distribution shift. In this work, we use mechanistic interpretability to study how robustness-relevant perturbations are represented in WAM activation space. Comparing activations across successful …
Jihoon Hong, Julian Skifstad, Qiyue Dai, Alice Chan, Glen Chou · 📄 PDF
AeroAct: Action-Centered World-Action Models for Language-Conditioned Quadrotor Flight
Language-conditioned quadrotor flight requires a policy to ground semantic goals, anticipate the visual consequences of ego-motion, and output control references that remain smooth and dynamically executable under rapidly changing first-person views. Existing aerial vision-language navigation and vi…
Xinhong Zhang, Qiyuan Zhu, Yubo Huang, Haolin Chen, Runqing Wang, Yuhao Mo, Zhongxin Chen, Yu Hu, Xinjiang Wang, Jian Su… · 📄 PDF
CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking
Dynamic target tracking is essential for Unmanned Aerial Vehicles (UAVs) operating in complex urban environments, where both the target and the camera viewpoint change continuously. Existing Vision-Language-Action (VLA) policies can track visible targets effectively, but their performance often degr…
Ruilong Ren, Songsheng Cheng, Yunpeng Zhou, Hanxuan Chen, Xiangyue Wang, Tianle Zeng, Shuai Yuan, Binbo Li, Hanzhong Guo… · 📄 PDF
Risk-Aware Belief Control Barrier Functions over Random Finite Sets
Ensuring robot safety in unknown, dynamic environments is a fundamental requirement. It involves inferring the states of an unknown and time-varying number of moving objects from noisy, incomplete measurements. We address safe control under the induced multi-object state uncertainty with a risk-awar…
Shaohang Han, Gang Chen, Yixi Cai, Ignacio Torroba, Ivan Stenius, Patric Jensfelt, Javier Alonso-Mora, Jana Tumova · 📄 PDF
Learning Agile Navigation in Crowded Environments for Quadruped Robots
Navigating dynamic and crowded environments presents significant challenges for quadruped robots due to severe sensor occlusion and unpredictable human motion. Existing approaches face a trade-off: model-based methods, such as Velocity Obstacles (VO), theoretically guarantee safety but rely on accur…
Shuyu Wu, Zeyu Liu, Tianbao Zhang, Fanxing Li, Fangyu Sun, Mingkang Xiong, Wei Xi, Wenxian Yu, Danping Zou · 📄 PDF
SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment
CAD-to-image alignment aims to estimate an object's 9D pose (rotation, translation, and anisotropic scale) from a single RGB image, enabling applications in robotics and augmented reality. Recent zero-shot methods use visual foundation models to match image regions to CAD models, yet typically their…
Saad Ejaz, Miguel Fernandez-Cortizas, Javier Civera, Holger Voos, Jose Luis Sanchez-Lopez · 📄 PDF
DriftWorld: Fast World Modeling through Drifting
Predictive world models enable robots to plan by imagining the outcomes of their actions, but their value for control hinges on generating many rollouts quickly. This creates a bottleneck for diffusion-based world models: multistep sampling makes each rollout expensive, limiting large-scale action s…
Susie Lu, Haonan Chen, Weirui Ye, Yilun Du · 📄 PDF
Goal-Oriented Semantic Communication for Distributed ISAC-Enabled Vehicle Coordination
Vehicle coordination at unsignalized intersections relies on accurate real-time vehicle state acquisition and reliable command-and-control (C&C) signal delivery. However, existing studies typically treat sensing, communication, and control separately, which may lead to redundant transmissions, outda…
Wenjie Liu, Yansha Deng · 📄 PDF
Catch, Throw, Repeat: Planning for Human-Robot Partner Juggling
Dynamic object exchange between humans and robots remains a challenging problem due to uncertainty in perception, timing, and contact-rich interaction. Human-robot juggling represents a particularly demanding instance of this problem, requiring precise real-time coordination, predictive motion plann…
Jonathan Rainer Lippert, Kai Ploeger, Abir Chowdhury, Hermann Müller, Jan Peters, Alap Kshirsagar · 📄 PDF
Assessing Physical Frailty and Fall-Risk Indicators with Social Robots: An in situ Evaluation with Older Adults
Frailty assessments are crucial to evaluate the risk of adverse events and the health and social care needs of older adults, yet their administration remains resource-intensive and typically relies on coarse clinical outcomes, such as task completion times, which may overlook biomechanical indicator…
Aniol Civit, Antonio Andriella, Alba Martínez, Joan Ars, Aida Ribera, Cristian Barrué, Guillem Alenyà · 📄 PDF
Scaling Behavior Foundation Model for Humanoid Robots
Humanoid control requires natural whole-body coordination, precise real-time responses to control signals, and robust generalization across diverse environmental contexts, making it a cornerstone for generalist embodied agents. Behavior Foundation Models (BFMs) have recently emerged as a promising s…
Weishuai Zeng, Kangning Yin, Xiaojie Niu, Shunlin Lu, Weixiang Zhong, Jiahe Chen, Feiyu Jia, Xiao Chen, Zirui Wang, Furu… · 📄 PDF
AHEAD: Anticipatory Hand-Driven Teleoperation via Human Intent Prediction
Direct hand-driven teleoperation maps an operator's hand motion to robot end-effector commands at every frame, enabling precise control, but it requires constant monitoring and correction during approach, grasp, and placement, which can be slow and fatiguing. For repetitive pick-and-place tasks, sup…
Seok Joon Kim, Junho Lee, Federica Spinola, Taein Kwon, Mohsen Moghaddam · 📄 PDF
Stigmergic Graph Memory: An Environment-Aware Approach for Many-to-Many Multi-Agent Pickup and Delivery
Automated fulfillment warehouses must continuously assign and execute pickup-and-delivery work while avoiding congestion. In many-to-many Multi-Agent Pickup and Delivery (MAPD), a request specifies a stock-keeping unit rather than fixed endpoints, requiring the controller to select an agent, source,…
Aditya Dutta, Joon-Seok Kim · 📄 PDF
ESAR: Event-Based Synthetic Aperture Reconstruction
Event cameras report asynchronous polarity events when changes in log--radiance exceed a fixed contrast threshold, producing signed temporal contrast measurements rather than conventional image frames. We formulate monocular event-based imaging as a synthetic-aperture inverse problem for a static gr…
Harbir Antil, Daniel Blauvelt, David Sayre · 📄 PDF
Towards Hierarchical Structure Understanding of Newspaper Images
Understanding newspaper images remains a challenging task due to their complex, nested hierarchical structures and dense, heterogeneous layouts. In this paper, we explore two complementary approaches for newspaper structure understanding. First, we present a modular bottom-up pipeline that combines …
William Mocaër, Solène Tarride, Thomas Constum, Merveilles Agbeti-Messan, Tom Simon, Clément Chatelain, Stéphane Nicolas… · 📄 PDF
Quantifying Training Membership Information in the Hyperspherical Embedding Geometry of Face Recognition Models
Face recognition models represent each face as an embedding vector on the unit hypersphere by clustering embeddings of the same identity while pushing different identities apart through angular-margin losses. Because these losses act only on training identities, non-member identities may form cluste…
Ünsal Öztürk, Sébastien Marcel · 📄 PDF
QuReC: All-in-One Image Restoration with Query-Specific Guidance and Local-Global Response Calibration
All-in-one image restoration aims to recover clean images degraded by multiple corruption types using a single unified model. Existing methods typically rely on image-level prompts or shared guidance to handle diverse degradations. However, such a paradigm becomes inadequate when degradations are sp…
Shen Zhou, Jinghui Zhang, Wenbo Huang, Xuwei Qian, Zhen Wu, Guangwen Peng, Zhiyuan Li, Ding Ding, Dian Shen, Fang Dong · 📄 PDF
DAPGNet: Dynamic Adaptive Physics-Guided Graph Diffusion Network for Hyperspectral Image Classification
Hyperspectral image (HSI) classification requires reliable pixel-relation modeling under spectral variability, mixed pixels, and heterogeneous boundaries. Existing graph-based HSI classifiers usually construct graph topology from spatial proximity, superpixel connectivity, or learned feature affinit…
Pengkun Wang, Weijia Cao, Ning Wang, Xiaofei Yang · 📄 PDF
Ray-based phase error correction for miniaturized DOE projector-based FPP under single-directional hyperbolic projection
Fringe Projection Profilometry (FPP) systems using miniaturized DOE pro-jectors often suffer from severe phase artifacts due to nonlinear projection characteristics and limited pattern controllability. We propose a ray-based phase error correction framework that models phase artifacts along projecti…
Seung-Jae Son, Yatong An, Jae-Sang Hyun · 📄 PDF
MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos
This paper presents MAGiSt3R, a multi-agent 3D reconstruction framework performing reconstruction and camera tracking for monocular RGB videos at almost 10 FPS. MAGiSt3R relies on a feed-forward model from the 3R family to process RGB videos and regress local point maps, and on a merging model, MAGM…
Ziren Gong, Xiaohan Li, Fabio Tosi, Ninghui Xu, Stefano Mattoccia, Jianfei Cai, Matteo Poggi · 📄 PDF
Structural-Semantic Reciprocal Learning for Unsupervised Visible-Infrared Person Re-Identification
Unsupervised visible-infrared person re-identification (USVI-ReID) is challenging due to the large modality gap and the lack of cross-modal identity annotations. Progressive association paradigms have been proposed to gradually bridge the gap, but they suffer from two critical bottlenecks: reliance …
Moyao Tian, Shijia Liu, Yan Yang, Xin Yuan, Minshi Chen, Wei Wang, Xiao Wang · 📄 PDF
Divergent Gaze Patterns in Artistic Viewing: Spatial and Temporal Signatures of Attention Across Autistic Individuals, Artists, and Neurotypical Observers
How different populations visually explore artworks bears on cognitive science and on accessibility design, yet most eye-tracking work in autism has used social scenes rather than art, and has analysed where the eyes land while ignoring when and in what order. We present a comparative free-viewing s…
Mohammed Amine Kerkouri, Daphné Senggaran, Renaud Jusiak, Océane Lehmann, Marouane Tliba, Claire Wardak, Emmanuelle Houy… · 📄 PDF
CRISP: Constrained Refinement via Iterative Squeezing Process for Robust Medical Image Segmentation under Domain Shift
Distribution shift in medical imaging remains a central bottleneck for the clinical translation of medical AI. Failure to address it can lead to severe performance degradation in unseen environments and exacerbate health inequities. Existing methods for domain adaptation are inherently limited by ex…
Yizhou Fang, Pujin Cheng, Yixiang Liu, Xiaoying Tang, Longxi Zhou · 📄 PDF
Beyond the Leaderboard: Design Lessons for Trustworthy Multimodal VQA
Healthcare multimodal AI must combine visual and textual evidence while remaining reliable and interpretable. Using MediaEval Medico 2025 as a retrospective GI endoscopy case study, we analyze design choices across nine documented systems for question answering and explanation quality. Parameter-eff…
Sushant Gautam, Vajira Thambawita, Michael A. Riegler, Pål Halvorsen, Steven A. Hicks · 📄 PDF
ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors
The reliability of deepfake detectors frequently degrades under black-box adversarial transfer, as these models often rely on fragile, architecture-dependent forensic cues. Existing transfer attacks often lack semantic awareness and struggle to maintain effectiveness under strict no-query constraint…
Christos Korgialas, Gabriel Lee Jun Rong, Dion Jia Xu Ho, Pai Chet Ng, Xiaoxiao Miao, Konstantinos N. Plataniotis · 📄 PDF
HoloGeo: Mitigating Landmark Bias in Geo-localization via Evidence-Driven Reasoning
Recent advances in Vision-Language Models (VLMs) have significantly improved image geo-localization, yet existing models remain susceptible to landmark bias, causing them to overlook geographical cues or form spurious correlations, ultimately resulting in inaccurate localization. To systematically i…
Pengcheng Zhou, Xuanyu Liu, Yanchen Yin, Bobo Li, Shengqiong Wu, Mong-Li Lee, Wynne Hsu · 📄 PDF
Motion-Conditioned Multi-View Fusion for Myocardial Infarction Localization from Echocardiography
Myocardial infarction (MI) remains a leading cause of mortality worldwide. Echocardiography (Echo) is a widely available modality for MI assessment, where regional wall motion abnormality is a key indicator. Prior learning based methods for myocardial motion analysis often use handcrafted descriptor…
Guang Yang, Wentian Xu, Siyu Wang, Betty Raman, Lei Li, Vicente Grau · 📄 PDF
Hierarchical Denoising For Multi-Step Visual Reasoning
Video models are evolving into vision foundation models, yet they still lack human-like multi-step reasoning. Streaming autoregressive diffusion models are efficient but limited in reasoning, while bidirectional diffusion enables global revision with high inference costs due to dense frame-level den…
Zezhong Qian, Xiaowei Chi, Chak-Wing Mak, Tianze Zhou, Ruibin Yuan, Yuhan Rui, Hengzhe Sun, Zhuoqun Wu, Yuming Li, Siyua… · 📄 PDF
Kernel weighted importance sampling for off-policy evaluation in contextual bandits
This article presents a novel estimator for performing off-policy evaluation using only offline data for contextual bandits. The proposed estimator, Kernel-WIS is demonstrated to be asymptotically consistent and to empirically outperform strong baselines (including vanilla weighted importance sampli…
Joshua Spear, Matthieu Komorowski, Rebecca Pope, Neil J Sebire, Erica E. M. Moodie · 📄 PDF
An Introduction to Sparse Identification of Nonlinear Dynamics for Engineering Applications
Many engineering problems involve phenomena whose governing equations are poorly characterized or only partially known. Surrogate modeling techniques such as neural networks can capture the behavior of these systems, but they typically demand large training datasets that are difficult to obtain in e…
Yao Cheng Li, Ana Larrañaga, Steven L. Brunton, Urban Fasel · 📄 PDF
Evaluating covariate balance for long time horizon Markov decision processes
This article explores the application of covariate balance diagnostics for detecting the presence of hidden confounding/model miss-specification in studies applying offline reinforcement learning (RL) to deriving optimal treatment recommendations. The results demonstrate that, either there is a high…
Joshua Spear, Rebecca Pope, Neil J Sebire · 📄 PDF
AlphaWiSE: Adaptive Weight Interpolation for Continual Multimodal Representation Learning
Multimodal models such as CLIP learn a shared embedding space for cross-modal retrieval, but continual adaptation to sequentially arriving data can disrupt the cross-modal alignment acquired from earlier phases. Conventional continual-learning methods return a single checkpoint, which commits every …
Sarthak Jain, Qiran Hu, Zhen Zhu, Yaoyao Liu · 📄 PDF
Learning in Infinitesimal Non-Compositional Sketches
This paper develops a categorical framework -- Learning in Infinitesimal Non-Compositional Sketches (LINCS) -- as the repair of non-compositionality: failures of diagrams to factor through quotient sketches lifted to the tangent category setting. Machine learning problems are specified as sketches: …
Sridhar Mahadevan · 📄 PDF
Concept-Guided Spatial Regularization for World Models in Atari Pong
World models are usually evaluated as components of model-based reinforcement learning (MBRL) systems, while the world models themselves are rarely studied in isolation. We examine five representative visual world-model agents in Atari Pong: DreamerV3, DIAMOND, TWISTER, Simulus, and STORM. After rep…
Yukuan Lu, Zaishuo Xia, Weyl Lu, Yubei Chen · 📄 PDF
On-Policy Delta Distillation
On-policy distillation is an alternative post-training method in reinforcement learning that alleviates the constraints imposed by reward models by providing token-level supervision from a teacher model. Although on-policy distillation has been studied and applied across various settings, its fundam…
Byeongho Heo, Jaehui Hwang, Sangdoo Yun, Dongyoon Han · 📄 PDF
RTS Smoother-Guided Learning of Physics-Based Neural Differential Models
Ordinary differential equations (ODEs) are widely used to model dynamical systems in physics, biology, neuroscience, and physiology, but in many applications some equations of the dynamics are unknown and only a subset of the state variables are measured. We propose a hybrid neural--physics framewor…
Ahmet Demirkaya, Georgios Stratis, Tales Imbiriba, Zachary D. Danziger, Deniz Erdogmus · 📄 PDF
BadWAM: When World-Action Models Dream Right but Act Wrong
World-action models (WAMs) are emerging as a promising foundation for embodied control: rather than predicting actions alone, they learn representations that couple action generation with future world prediction. This coupling is often viewed as a source of robustness, interpretability, and safety, …
Qi Li, Xingyi Yang, Xinchao Wang · 📄 PDF
Delocalization of bias in unadjusted Hamiltonian Monte Carlo and underdamped Langevin
Unadjusted samplers such as unadjusted Hamiltonian Monte Carlo and underdamped Langevin are well-known to be biased. Metropolis--Hastings adjustment has been conventionally incorporated into Hamiltonian Monte Carlo to eliminate the bias. However, this adjustment can significantly increase the iterat…
Yifan Chen, Xiaoou Cheng, Jonathan Niles-Weed, Jonathan Weare · 📄 PDF
NeuronSoup: Evolving Asynchronous, Shared-Neuron Temporal Graphs without Backpropagation
We present NeuronSoup, a neural computation architecture that replaces synchronous layer-by-layer processing with asynchronous, delay-mediated signal propagation through a pool of shared neurons. Each path in the network routes a continuous-valued signal from one input neuron to one output neuron th…
Subodh Kalia · 📄 PDF
Data Driven Block Replacement Scheduling
We develop data-driven algorithms for maintaining $N$ independent identical machines under a \textit{block replacement policy}, in which each machine is replaced upon failure and all machines are jointly replaced at regular intervals of length $k$. The goal is to learn the cost-minimizing interval $…
Aniruddhan Ganesaraman, VIdyadhar Kulkarni · 📄 PDF
Mutable Low-Rank Sketches for Retrain-Free Recommendation
A common bottleneck in two-stage recommendation is embedding staleness: when a user rates a new item, their embedding remains fixed until the next retrain cycle. We propose mutable sketches, which store each user's preferences in a KP-tree (a sparse segment tree with sum aggregation), fit a low-rank…
Hector J. Garcia, Nick Clayton · 📄 PDF
Decoding Market Emotion from Blockchain Activity: A Data-Driven Sentiment Classifier
The growing use of Bitcoin as a decentralized digital asset and investment tool has sparked strong interest in understanding its market behavior. This study presents a new approach to analyze Bitcoin market sentiment by combining on-chain and financial data with social media posts. Unlike models tha…
Arthur G. Bubolz, Abreu Quevedo, Giancarlo Lucca, Rafael A. Berri, Eduardo Borges, Bruno L. Dalmazo · 📄 PDF
Online Neural Space Time Memory for Dynamic Novel View Synthesis
Online novel view synthesis from multi-view streaming videos faces a fundamental trade-off: maintaining a persistent, long-horizon memory to reconstruct temporarily occluded regions while operating under strict real-time constraints. While Test-Time Training (TTT) offers a powerful memory mechanism,…
Baback Elmieh, Lynn Tsai, Zeman Li, Srinivas Kaza, Tiancheng Sun, Gabor Csapo, Ali Behrouz, Yuan Deng, Stephen Lombardi,… · 📄 PDF
MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators
MeanFlow generators achieve fast few-step sampling by predicting average velocities over time intervals, making them attractive for efficient generation. Reinforcement learning (RL) has become a powerful way to align diffusion and flow models with human preferences and task-specific objectives. In p…
Yushi Huang, Xiangxin Zhou, Jun Zhang, Liefeng Bo, Tianyu Pang · 📄 PDF
MedFailBench: A Clinician-Built Open-Source Benchmark for Medical AI Safety Boundary Inspection
Most medical AI benchmarks measure whether a model knows the correct answer. MedFailBench asks a different question: which safety boundary failed? We present a clinician-built synthetic benchmark and failure atlas that labels medical AI errors by severity (1--5) and safety gate type (missed urgent e…
Goktug Ozkan · 📄 PDF
Benchmarking Multimodal Large Language Models for Scientific Visualization Literacy
Multimodal large language models (MLLMs) are increasingly used to interpret visualizations, yet current evaluations remain largely chart-centric and provide limited evidence of understanding of scientific visualization (SciVis). We benchmark six MLLMs on the scientific visualization literacy assessm…
Patrick Phuoc Do, Chau M. Ta, Chaoli Wang · 📄 PDF
T^2MLR: Transformer with Temporal Middle-Layer Recurrence
Transformer reasoning is limited by autoregressive decoding, which repeat edly compresses rich hidden computation through token space and makes it difficult for intermediate reasoning states to persist across time. We in troduce Transformers with Temporal Middle-Layer Recurrence (T2MLR), a transform…
Ziyang Cai, Xingyu Zhu, Yihe Dong, Yinghui He, Sanjeev Arora · 📄 PDF
Can We Trust Item Response Theory for AI Evaluation?
AI benchmarks increasingly leverage item-level statistical models, particularly item response theory (IRT), to estimate model capabilities, rank systems, select informative examples, and diagnose benchmark quality. However, AI benchmark data often departs from the data regime of human testing, for w…
Han Jiang, Sunbeom Kwon, Jinwen Luo, Ziang Xiao, Susu Zhang · 📄 PDF
Plover: Steering GUI Agents through Plan-Centric Interaction
Graphical user interface (GUI) automation remains challenging in real-world environments, where dynamic layouts, unexpected dialogs, and evolving interface states can cause autonomous agents to drift from user intent. Recent vision-based multimodal agents improve flexibility by operating directly ov…
Madhumitha Venkatesan, Shicheng Wen, Jiajing Guo, Jorge Piazentin Ono, Liu Ren, Dongyu Liu · 📄 PDF
Subjective Risk Decomposition: A New View for Uncertainty Quantification
We present a novel viewpoint for uncertainty quantification. Uncertainty measures are not primitives, in need of axioms and argumentation, but instead consequences, of higher-level modelling decisions. We show how epistemic and aleatoric uncertainty measures can be derived via decomposition of a sub…
Raghad Alamri, Michele Caprio, Gavin Brown · 📄 PDF
Mask-Aware Policy Gradients for Diffusion Language Models
Reinforcement learning has proven effective for improving reasoning in large language models, but extending it to Masked Diffusion Language Models (MDLMs) remains challenging due to the intractability of the log-likelihood estimation. Existing approaches approximate this log-likelihood by modeling o…
Haran Raajesh, Kulin Shah, Adam Klivans, Philipp Krähenbühl · 📄 PDF
Self-Evolving Human-Centered Framework for Explainable Depression Symptom Annotation
Annotation quality is a major bottleneck in building reliable and explainable artificial intelligence (XAI) systems for mental health research. In depression-related datasets, labels are often assigned without structured evidence, symptom-level justification, or traceable alignment with the criteria…
Hoang-Loc Cao, Van Pham, Truong Thanh Hung Nguyen, Phuc Truong Loc Nguyen, Phuc Ho, Veronica Whitford, Hung Cao · 📄 PDF
MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization
Real repository issues routinely include visual evidence such as screenshots, error dialogs, rendered UI states, and logs, yet repository-level issue localization is evaluated mostly as a text-only task. Existing multimodal SE benchmarks evaluate end-to-end repair, entangling localization with patch…
Shaoxiong Zhan, Shi Hu, Boyu Feng, Hai Lin, Andrew Gong, Zhengda Zhou, Jiaying Zhou, Yunyun Hou, Hao Su, Hai-Tao Zheng · 📄 PDF
Symbal: Detecting Systematic Misalignments in Model-Generated Captions
Multimodal large language models (MLLMs) often introduce errors when generating image captions, resulting in misaligned image-text pairs. Our work focuses on a class of captioning errors that we refer to as systematic misalignments, where a recurring error in MLLM-generated captions is closely assoc…
Maya Varma, Jean-Benoit Delbrouck, Sophie Ostmeier, Akshay Chaudhari, Curtis Langlotz · 📄 PDF
When Words Are Safe But Actions Kill: Probing Physical Danger Beyond Text Safety in Hidden-State Risk Space
Large language models (LLMs) increasingly serve as high-level planners for embodied agents, where linguistically benign instructions can become unsafe once grounded in the physical world. We study whether this physically grounded danger is the same safety problem as ordinary text-level content dange…
Weimeng Wang, Ziqiang Wang, Zihang Zhan, Chuanpu Fu, Qi Li, Ke Xu · 📄 PDF
In-Place Tokenizer Expansion for Pre-trained LLMs
A tokenizer fixed at the start of pre-training allocates vocabulary in proportion to the pre-training corpus, reflecting the deployment priorities at that time. When those priorities shift, languages added later are split into many more tokens per word, which can raise latency, compute, and energy c…
Jimmy T. H. Smith, Tarek Dakhran, Alberto Cabrera, Simon S. Lee, Paul Pak, Aditya Tadimeti, Tim Seyde, Maxime Labonne, A… · 📄 PDF
AutoSynthesis: An agentic system for automated meta-analysis
Evidence synthesis is crucial for turning primary research into reliable knowledge for science, medicine, education, and policy. Yet, quantitative evidence synthesis remains largely manual and difficult to scale. Here, we introduce AutoSynthesis, an end-to-end multi-agent system for automated meta-a…
Moein Taherinezhad, Sebastian Maier, Gerardo Vitagliano, Francesco Pierri, Stefan Feuerriegel · 📄 PDF
teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Data
Traffic agencies now have access to large volumes of video-derived data for studying safety and congestion. Most of these data are observational and collected without interventions, which makes causal questions such as "How would rain change traffic density?" difficult to answer. We present teLLMe, …
Qiwei Li, Jorge Ortiz · 📄 PDF
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
Recent advances in Tool-Integrated Large Language Models have made web search a core capability of information-seeking agents. However, as interaction histories grow, agents increasingly struggle to track task progress. When search attempts fail to yield useful evidence, current single- and multi-ag…
Yuyao Zhang, Junjie Gao, Zhengxian Wu, Jiaming Fan, Jin Zhang, Shihan Ma, Yao Yao, Weiran Qi, Chuyan Jin, Guiyu Ma, Xing… · 📄 PDF
Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents
Security-agent evaluations commonly measure peak offensive capability under generous inference budgets, emphasizing vulnerability discovery, exploit development, penetration testing, and CTF completion. Such measurements are useful but incomplete: in operational security, every reasoning step, tool …
Paul Kassianik, Blaine Nelson, Yaron Singer · 📄 PDF
SceneBind: Binding What and Where Across Vision, Audio and Language
We present SceneBind, an omni-modal representation of realistic scenes with joint semantic and 3D spatial understanding across vision, audio and language. Existing omni-modal encoders excel at instance-level semantics (i.e., what is present), but often lack explicit spatial structure (i.e., where it…
Mingfei Chen, Zijun Cui, Ruoke Zhang, Hyeonggon Ryu, Eli Shlizerman · 📄 PDF
Pretraining Data Can Be Poisoned through Computational Propaganda
Poisoning pretraining data can introduce harmful behaviors to LMs that are difficult to detect and mitigate. Prior work on poisoning pretraining data has largely exploited established data sources such as Wikipedia, which do not represent the large scale and heterogeneity typical of pretraining corp…
Victoria Graf, Hannaneh Hajishirzi, Noah A. Smith, David Kohlbrenner, Kyle Lo · 📄 PDF
SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions
Editing the figures in a research paper is a routine and time-consuming part of everyday research practice: authors relabel components, rearrange panels, and restyle visuals as they revise their manuscripts. Automating this editing workflow under a natural-language instruction, however, is challengi…
Yasheng Sun, Zezi Zeng, Yifan Yang, Chong Luo, Wenyi Wang, Ziwei Liu, Jürgen Schmidhuber · 📄 PDF
RoboTTT: Context Scaling for Robot Policies
Recent robot foundation models operate with single-step or short-history visuomotor context. We introduce Test-Time-Training Robot Policies (RoboTTT), a robot model and training recipe that scale visuomotor context to 8K timesteps, three orders of magnitude beyond state-of-the-art policies, without …
Yunfan Jiang, Yevgen Chebotar, Ruijie Zheng, Fengyuan Hu, Yunhao Ge, Jimmy Wu, Tianyuan Dai, Scott Reed, Li Fei-Fei, Yuk… · 📄 PDF
Mapping Diplomatic Representation in Europe, 1648-1715
This paper introduces new data on diplomatic representation in Europe between 1648 and 1715, drawn from Band I of the Repertorium der diplomatischen Vertreter aller Lander. The data comprise 13,344 diplomatic missions, exchanged among 141 sending and 201 receiving polities, and 8,852 individual repr…
Magnus Lundgren · 📄 PDF
Equilibrium stability as a driver of cooperation among Q-learners
Algorithmic collusion among pricing algorithms has raised concerns about sustained supra-competitive prices and their implications for social welfare. Existing work has largely focused on the probability that reinforcement-learning algorithms converge to cooperative strategies, typically under the a…
Janusz M. Meylahn, Maximilian Schäfer · 📄 PDF
Messy Research, Certification and the Monetization of Science
I study how cheaper AI-assisted research changes the institutions that certify science. AI lowers the cost of producing a polished manuscript faster than it lowers the cost of judging whether the underlying contribution is valuable. Polish therefore loses information, entry expands and the average q…
Johan Fourie · 📄 PDF
Adaptive Ad Load Design for Sponsored Search Markets: Evidence, Theory, and Deployment
Ad-load design is a central supply-side decision in sponsored search: more sponsored slots can raise revenue, but may crowd out organic results and degrade user outcomes. We study this trade-off using a large-scale randomized field experiment on an Android app store, where over five million users ar…
Mohammad Rashid, Hema Yoganarasimhan · 📄 PDF
Causal Discovery of Radiation Response Mechanisms in Human Cells
Next-generation sequencing technologies, including RNA-sequencing, provide genome-wide measurements of gene expression and enable broad explorations of biomarkers and mechanisms underlying disease and treatment response. Bioinformatics tools for processing this data, such as differential expression …
Ashka Shah, Rick Stevens · 📄 PDF
LATTICE: Graph Self-Supervised Learning for Multimodal Spatial Omics Integration
Spatially resolved omics studies increasingly combine transcriptomic and epigenomic assays, yet downstream analysis is often still performed using single-modality pipelines. We present LATTICE (Latent Alignment of Tissue-level and Transcriptomic Information for Cross-modal Embedding), a graph-based …
Jagan Mohan Reddy Dwarampudi, Veena Kochat, Suresh Satpati, Kunal Rai, Tania Banerjee · 📄 PDF
A vision foundation model for single-cell biology via spatial gene cartography
Most single-cell foundation models are adapted from language models, representing each cell as a sequence of gene tokens. This discards the relationships among genes and often the magnitude of their expression. We present scVision, a vision foundation model that instead renders each cell as a contin…
Ridvan Yesiloglu, Sakib Mostafa, James Zou, Ash Alizadeh, Jiajun Wu, Lei Xing, Ehsan Adeli, Md Tauhidul Islam · 📄 PDF
Exact Decomposition of Adversarial Dual-Objective Value Functions, with Applications to Optimal Drug Dosing
Hamilton-Jacobi Reachability (HJR) is a central framework in safe control theory. While HJR has traditionally focused on a few fundamental tasks, there is increasing interest in scaling to more complex objectives. Recent works have studied the exact decomposition of the value functions for two funda…
Dylan Hirsch, William Sharpless, Sylvia Herbert · 📄 PDF
Analyzing Post-transcriptional Regulation in Stochastic Gene Expression Models Using Partitioned Poisson Arrivals
Gene expression is a stochastic process that allows for fluctuations in protein levels that can give rise to phenotypic heterogeneity within a population of genetically identical cells. Thus, there is great interest in quantifying how natural variation (noise) in gene expression is impacted by cellu…
Kenny Wong, Argenis Arriojas, Sho Inaba, Hodjat Pendar, Abhyudai Singh, Rahul Kulkarni · 📄 PDF
Marker-free deformable registration and fusion for augmented reality-guided positive margin localization during tumor resection surgery
Positive margins in head and neck oncologic surgery require mapping specimen-side pathology findings to the patient resection bed. This is challenging because pathologists identify the positive margin on slices of the resected, deformed specimen, while surgeons must relocate the corresponding site o…
Yue Yang, Annie Benson, Matthieu Chabanas, Jason Slagle, Thomas Myles, Matthew B. Weinger, Jon S. Heiselman, Michael I. … · 📄 PDF
Ripple: An Open, AI-Formalized Lean 4 Framework for Computing with CRNs
We present Ripple, an open, AI-formalized Lean 4 framework for the mathematics of computing real numbers with chemical reaction networks (CRNs). Ripple formalizes the full ladder of models -- the GPAC / CRN continuum and the CRN-computable reals, the large-population-protocol (LPP) compilation pipel…
Ho-Lin Chen, Xiang Huang · 📄 PDF
Evaluating Encoding Strategies for Closed-Loop Classification in Biological Neural Networks
Interfacing with Biological Neural Networks (BNNs) requires encoding information into stimulation patterns that can be effectively processed and that enable the underlying system to adapt. Nevertheless, the role of stimulation encoding remains poorly understood. In this work, we compare multiple enc…
Martin Schottlender, Veronika Volkova, Pengjie Zhou, Ruifeng Zheng, Frank H. P. Fitzek, Pit Hofmann · 📄 PDF
Unified Uncertainty Quantification Framework Bridging Noisy Quantum Backends Across Variational Quantum Algorithms and Quantum Signal Processing
We present an uncertainty quantification (UQ) framework for application level benchmarking and characterization of noisy quantum backends. The framework compares two workload classes under one statistical pipeline: noisy intermediate scale quantum (NISQ) variational quantum algorithms (VQAs) and Qua…
Priyabrata Senapati, Vibin Abraham, Qiang Guan, Bo Peng · 📄 PDF
Towards Reliable AI-Assisted Analog Design: Template-Constrained LLM Agents for SAR ADC Generation
While Large Language Models (LLMs) have demonstrated significant capability in software code generation, their application to analog Electronic Design Automation (EDA) is bottlenecked. Owing to limited circuit topology understanding and data, directly prompting LLMs and multimodal models leads to ha…
Dimple Vijay Kochar, Hae-Seung Lee, Anantha P. Chandrakasan · 📄 PDF
CODA: How to Mitigate ColumnDisturb for (Almost) Free?
ColumnDisturb is a new data-disturbance error in which activations to an aggressor row cause bitflips in a victim row located hundreds of rows away (intra-subarray bitflips) and in victim rows in adjacent subarrays (inter-subarray bitflips). Intra-subarray ColumnDisturb can be tolerated by solutions…
Moinuddin Qureshi · 📄 PDF
CIMERA: Compute-in-Interconnect and Memory with Reconfigurable Precision for LLM Inference
LLM impose significant computational and memory demands, creating challenges for energy-efficient inference across platforms ranging from data centers to power-constrained edge devices. Weight precision plays a critical role in balancing inference accuracy, throughput, and energy consumption, while …
Yue Jiet Chong, Yimin Wang, Wei Zhang, Xuanyao Fong · 📄 PDF
Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space Correlations
Video diffusion transformers (vDiTs) generate high quality video but introduce extremely high compute cost due to the long diffusion timesteps and self attention computation. As diffusion timesteps are reduced, the computation cost of self attention becomes the dominant bottleneck. Existing accelera…
Wenxuan Miao, Haosong Liu, Weiming Hu, Zihan Liu, Aiyue Chen, Jianlin Yu, Yiwu Yao, Yiming Gan, Jieru Zhao, Jingwen Leng… · 📄 PDF
Jack of All Scales: A Versatile FPGA Tensor Block for MXFP Precisions
Modern deep learning workloads increasingly rely on narrow numerical formats to improve efficiency and reduce memory footprint. The recently standardized microscaling floating-point (MXFP) family of formats, including MXFP8, MXFP6, and MXFP4, offers a practical approach to low-precision inference, y…
Marwan Mekhemer, Ahmed Elsousy, Balaji Venkatesh, Raphael Rowley, Vaughn Betz, Nachiket Kapre, Andrew Boutros · 📄 PDF
Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation
Real-world deployment of embodied agents requires active exploration, visual grounding, and interactive intent disambiguation. However, existing frameworks often rely on privileged simulator states or assume complete instructions, bypassing realistic deployment challenges. To bridge this gap, we pre…
Boyu Mi, Mengchen Ma, Yifei Yao, Xing Gao, Junting Chen, Yangzi Li, Zihou Zhu, Guohao Li, Zhenfei Yin, Tai Wang, Yao Mu,… · 📄 PDF
WAVE-Stereo: Warp-Aligned Volume Encoding for Stereo Matching
Existing iterative stereo matching methods primarily adopt two types of correspondence representation: explicit matching search via correlation volumes and local residual refinement via warped features, yet the two remain separately modeled. We propose WAVE-Stereo, built on a core insight: correlati…
Zehan Liu, Yage He, Xianwu Gong · 📄 PDF
Anatomy of Uncertainty: Expressive Descriptors of Robotic Manipulator Motion for Non-verbal Communication in Human-Robot Collaboration
Robots operating in human-robot collaboration must communicate not only their intended actions but also uncertainty arising from incomplete or ambiguous perception. This work introduces a mathematical framework for expressing perceptual uncertainty through robotic manipulator motion. Drawing on Laba…
Ridhima Bector, Souravik Dutta, Poornima Ramachandran, Ree Yan Yeoh, Jui Hien Tan, Domenico Campolo, Bernhard Johannes S… · 📄 PDF
Towards a Modular Bin-picking Framework for Handling Object Pose Uncertainties
In recent years, there has been growing interest in robust robotic systems for precise bin-picking applications. To achieve reliable performance, such systems must address errors arising from both the object pose estimation and the grasping process. Although various approaches have been proposed, th…
Frederik Hagelskjær · 📄 PDF
nuTruck: Benchmarking Autonomous Driving Planning for Distributed Electric-drive Trucks
The dominance of traditional rule-based methods in autonomous driving has gradually been replaced by learning-based approaches. While learning-based planners have achieved considerable success in passenger vehicles, their performance on heavy-duty trucks, particularly modern distributed electric-dri…
Jinyu Miao, Pu Zhang, Yifei He, Chengyao Zhang, Kun Jiang, Ke Wang, Mengmeng Yang, Diange Yang · 📄 PDF
The Nonsmooth Impact Direction (NSID) of Robotic Systems
Collisions of rigid-link robots and rigid environments are often modeled as instantaneous events. Under this idealization, the impact forces become impulsive and the system velocities nonsmooth. In this work, we systematically analyze pre- and post-impact velocities focusing on what we refer to as t…
Annika Kirner, Christian Ott · 📄 PDF
Dynamical Vehicle Orienteering Problem for Multi-Rotor Unmanned Aerial Vehicles
This paper introduces the Dynamical Vehicle Orienteering Problem (DVOP), a generalization of the Orienteering Problem (OP). The OP maximizes the reward collected from spatial targets under a limited travel budget; the DVOP extends it by accounting for both external and vehicle-actuated forces. We st…
František Nekovář, Matej Novosad, Martin Saska, Robert Pěnička · 📄 PDF
Vision-Based Obstacle Separation for Strawberry Harvesting in Clusters Using Hierarchical Reinforcement Learning
Selective harvesting in clustered strawberry environments is challenging because ripe fruits are often occluded by surrounding unripe fruits, making direct grasping unreliable. To address this problem, this paper proposes a hierarchical reinforcement learning framework, termed VGPA, which integrates…
Teng Li, Hanfei Shi, Chunjiang Zhao, Ya Xiong · 📄 PDF
A Deployed Hybrid Vehicle-in-the-Loop Platform for Validating Cooperative Perception
European safety regulation now permits a large share of automated-driving homologation evidence to be produced virtually, provided a validated physical-virtual facility generates it. We present a deployed hybrid Vehicle-in-the-Loop (ViL) platform that couples a real instrumented vehicle with a CARLA…
Anastasia Bolovinou, Giorgos Hadjipavlis, Markos Antonopoulos, Panagiotis Tachtalis, Konstantinos Petousakis, Konstantin… · 📄 PDF
Learning Robust Execution in Robotic Manipulation with Agentic Reinforcement Learning
Robotic manipulation poses fundamental challenges due to uncertainty, long-horizon execution, and compounding errors, which can easily destabilize execution and lead to task failure. Although recent vision-language-action (VLA) models exhibit strong generalization, they typically lack explicit mecha…
Xiaopeng Zhang, Yueyang Weng, Qi Liu, Yongjin Mu, Yanjie Li · 📄 PDF
Merging Reaction to Cognition: A Hybrid Cognitive Strategy for Odour Source Localisation in Natural Environments
Chemical pollutants released into the environment are transported by turbulent flows, generating complex, intermittent plume structures that threaten ecosystems and human health. Rapid localisation of emission sources is critical, and field robots equipped with chemical sensors provide a viable mean…
Hugo Magalhães, Rui Baptista, Lino Marques · 📄 PDF
Learning Forward & Reverse Skills from a Single Unfinished Demonstration for Constrained Manipulation Tasks
Learning from demonstration (LfD) enables robots to learn manipulation skills directly from expert demonstrations but remains challenging for contact-rich tasks involving geometric constraints and force interaction. Existing approaches typically require multiple complete demonstrations and do not su…
Yexin Hu, Haoyi Zheng, Johannes Heidersberger, Dongheui Lee · 📄 PDF
S-squared-VLA: Decoupling Semantic and Spatial Streams in Vision-Language-Action Models for Autonomous Driving
Vision-Language Models (VLMs) have demonstrated remarkable potential for high-level reasoning in autonomous driving, yet they fundamentally struggle to generate precise, low-level control actions. This limitation is rooted in a semantic-physical gap caused by the inherent mismatch between discrete l…
Jianguo Yu, Rukang Wang, Duanfeng Chu, Chen Wang, Renju Feng, Liping Lu · 📄 PDF
Discriminative Barrier Functions for Safe Adversarial Imitation Learning from Observation
Inverse Reinforcement Learning (IRL) algorithms are powerful tools for learning from and generalizing expert demonstrations, but they often rely on unconstrained exploration, rendering them unsafe for real-world deployment. Meanwhile, Control Barrier Functions (CBFs) can guarantee the safety of cont…
Anubhav Vishwakarma, Bhaumik Mehta, Caleb Hsu, Byron Boots, Karen Leung, Tyler Han · 📄 PDF
GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch
World Action Models (WAMs) improve robot policy learning by jointly modeling actions and future visual observations, using future scene evolution as dense supervision for physically grounded action generation. However, a common design in existing WAMs is to explicitly generate future videos at infer…
GigaWorld Team, Angen Ye, Angyuan Ma, Boyuan Wang, Chaojun Ni, Fangzheng Ye, Guan Huang, Guo Li, Guosheng Zhao, Haodong … · 📄 PDF
AeroMap3D: Anchoring Monocular UAV 6-DoF Localization to Visual-Geometric-Semantic Map Priors
We present AeroMap3D, a monocular 6-DoF UAV localization system that anchors onboard imagery to visual, geometric, and semantic map priors for GNSS-denied navigation. AeroMap3D addresses two fundamental challenges in map-referenced aerial localization: the cross-view discrepancy between UAV imagery …
Zhiyun Deng, Luis Sentis · 📄 PDF
Industrial Dexterity Benchmark: A Hardware-Software Benchmarking Platform for Industrial Dexterous Manipulation
Dexterous manipulation remains a critical bottleneck in industrial automation; tasks such as cable routing, connector insertion, and precision assembly still rely heavily on manual labor despite decades of robotics research. This work presents a progression from classical, modular robotics pipelines…
Honglu He, Jacob Laufer, Zhiwu Zheng, David Elkan-gonzalez, Raman Goyal, Xinyi Li, Su Lu, Mishek Musa, Berke Saat, Nicol… · 📄 PDF
PhysClaw-0: A Symbiotic Agentic System for Robot Autonomy via Language Corrections
Autonomous data collection governs the volume and quality of real-world trajectories for manipulation policy learning. Existing pipelines reduce human effort via self-resetting, VLM verification, or language-guided correction, yet episode-scoped fixes must be reissued whenever the same failure recur…
Boyuan Wang, Zhenyuan Zhang, Zhiqin Yang, Peijun Gu, Shuya Wang, Xiaofeng Wang, Xianghui Ze, Yifan Chang, Guosheng Zhao,… · 📄 PDF
Recursive ArUco Markers: A Scalable Fiducial Marker Design for Unmanned Aerial Vehicle Landing Pads
Unmanned Aerial Vehicles (UAVs) increasingly rely on visual fiducial markers for autonomous navigation and precision landing. However, standard markers suffer from limited operational ranges, becoming undetectable when the camera is either too far or too close. While recursive and fractal markers ha…
Rafael Munoz-Salinas, Francisco Jose Romero-Ramirez, Sergio Garrido-Jurado · 📄 PDF
Towards Enhancing 3D Spatial Reasoning in Medical Multimodal Large Language Models
While Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in 2D medical image understanding, their extension to 3D volumetric imaging remains hindered by prohibitive annotation costs and dataset opacity. Current data formats, predominantly consisting of rigid Visual Questio…
Zhuoyuan Fu, Zeshang Li, Yiqiong Zhang, Hangui Lin, Yan Shu, Yan Li, Binyang Li, Yaru Zhao · 📄 PDF
PiVoT: A Variational Solution for Real-time Large-scale Multi-object Detection and Tracking under Heavy Clutter
Multi-object detection and tracking from noisy point clouds remain challenging in many data-scarce radar applications. Current Bayesian trackers based on Poisson measurement models offer a training-free solution but struggle to achieve accuracy and efficiency under severe clutter, large object popul…
Runze Gan, Qing Li, Simon J. Godsill, Mike E. Davies, James R. Hopgood · 📄 PDF
Fine-Grained Vision-Language Pretraining with Organ-Conditioned Pattern Tokens for CT Understanding
Computed tomography (CT) vision-language pretraining from paired volumes and radiology reports is a scalable yet challenging task. Existing methods commonly adopt global scan-report contrast, which is scalable but obscures heterogeneous organ evidence. Meanwhile, direct organ-level alignment remains…
Guoliang You, Xiaomeng Chu · 📄 PDF
The 2nd International StepUP Competition for Biometric Footstep Recognition: From Steps to Strides
The International StepUP Competition Series was launched to advance research in pressure-based footstep biometrics through a standardized and challenging evaluation framework. Using the large-scale StepUP-P150 dataset (with more than 200,000 high-resolution dynamic footsteps from 150 individuals) an…
Robyn Larracy, Anant Gupta, Gourav Gupta, Ethan Eddy, Maxime Devanne, Cyril Meyer, Jin-Chern Chiou, Yueh-Shan Lee, Zong-… · 📄 PDF
Thresholded Cross-Attention for Reliable Intensity-Chromaticity Fusion in Low-Light Image Enhancement
Low-Light Image Enhancement (LLIE) requires a careful balance among noise suppression, color fidelity, and efficiency. Recent HVI-based methods alleviate color entanglement by decoupling intensity and chromaticity, yet how reliably the two streams are fused again is an overlooked factor that largely…
Yanyi Wu, Xu Zhang, Junkai Chen, Laibin Chang, Jiaqi Ma, Shi Chen, Linwei Zhu, Jianglei Di, Huan Zhang · 📄 PDF
Cyclone: Diffusion Model for Cycle-Consistent Weather Editing from Unpaired Driving Data
Reliable perception under diverse weather conditions remains a major challenge for autonomous driving systems. A common strategy to improve robustness is either to synthesize adverse weather conditions for training perception models or to apply weather-removal techniques to recover clean inputs. How…
Thang-Anh-Quan Nguyen, Moussab Bennehar, Luis Guillermo Roldao Jimenez, Nathan Piasco, Dzmitry Tsishkou, Laurent Caraffa… · 📄 PDF
SIVA-RL: Sensitivity-Invariance Visual Alignment for Multimodal Reinforcement Learning
Reinforcement learning with verifiable rewards (RLVR) drives multimodal reasoning, but answer-level correctness does not guarantee that a vision-language model grounds its predictions in visual evidence. Existing visual-intervention methods contrast policy behavior on original and modified images, y…
Cheng Tang, Junzhi Ning, Min Cen, Wei Li, Xinyi Zeng, Pinxian Zeng, Rongbin Li, Qiming Zhu, Yuqiang Li, Junjun He, Yiron… · 📄 PDF
Peak-End-Net: A Peak-End Rule Inspired Framework for Generalizable Video Aesthetic Assessment
Video aesthetic assessment (VAA) aims to predict how aesthetically pleasing a video is, yet remains far less explored than other visual assessment tasks. Its progress is hindered not only by the scarcity of large-scale benchmarks, but also by the intrinsic subjectivity of aesthetic judgment, which i…
Geng Li, Haiwen Li, Rui Chen, Jing Tang, Lei Sun, Xiangxiang Chu · 📄 PDF
PlumeQuant: Uncertainty-aware consistency assessment of methane plume masks and emission-rate estimates
Imaging spectrometers increasingly distribute source-resolved methane plume products in which the plume mask, integrated mass enhancement (IME), plume length, emission rate, and uncertainty are physically and algorithmically linked. Using 63 EMIT-derived Carbon Mapper plume records from 27 scenes, w…
Parisa Masnadi Khiabani, Wolfgang Jentner, Alireza Rangrazjeddi, Michael C. Wimberly, Binbin Weng, David Ebert, Charles … · 📄 PDF
CF-Net: Conflict Fusion with Speaker Normalisation and Certainty Weighting for Ambivalence/Hesitancy Recognition
Detecting ambivalence and hesitancy (AH) in unconstrained video is challenging because the target signal is inherently ambiguous and expressed through subtle cross-modal incongruence rather than prototypical affect. We present CF-Net, a deep multimodal network submitted to the 3rd Edition of the AH …
Tung Hung Bui, Hong Hai Nguyen, Van Thong Huynh · 📄 PDF
Screening Is Effective for Visual Recognition
Vision Transformer (ViT) has been widely used as a powerful framework for modeling global dependencies among image patches. However, its core component, self-attention assigns softmax-normalized relative weights to all patches, making it difficult to evaluate the relevance between patches independen…
Shunya Shimomura, Kazuhiro Hotta · 📄 PDF
Task-Specific Feature Fusion Method for Multi-Task Affective Behavior Analysis
The 11th Affective Behavior Analysis in-the-wild (ABAW11) Multi-Task Learning Challenge requires a unified system to predict valence-arousal, categorical expressions, and facial action units from the official s-Aff-Wild2 images. Although these tasks are naturally related through facial behavior, our…
Jiajun Sun, Zhe Gao · 📄 PDF
M$^\text{4}$World: A Multi-view Multimodal Driving World Model for Interactive Object Manipulation and Minute-long Streaming
Driving-world generation has emerged as a core capability for scalable autonomous-driving simulation, yet existing methods remain limited in object-level controllability and long-horizon stability. We present M$^\text{4}$World, a Multi-view and Multimodal generative driving world model that synthesi…
Ke Cheng, Hanqiao Ye, Lei Shi, Yahui Liu, Yunhan Shen, Jingtao Dong, Zhenke Wang, Wenxuan Ao, Weixiang Xu, Kaining Huang… · 📄 PDF
From Pixels to States: Rethinking Interactive World Models as Game Engines
Building interactive worlds that respond coherently to player actions has long been a shared goal of computer graphics, games, and artificial intelligence. Recent video generative models provide a data-driven route toward this goal by predicting future observations conditioned on user actions, and a…
Zhen Li, Zian Meng, Shuwei Shi, Mingliang Zhai, Jiaming Tan, Chuanhao Li, Kaipeng Zhang · 📄 PDF
VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders
Video generative models commonly rely on latent spaces learned by 3D Variational Autoencoders (3D-VAEs). However, conventional 3D-VAEs are mainly optimized for pixel-level reconstruction, which can limit the semantic and spatio-temporal structure captured by their latents. Meanwhile, Video Foundatio…
Zhihao Xie, Junfeng Wu, Xinting Hu, Junchao Huang, Li Jiang · 📄 PDF
An Efficient Newton Algorithm for Nonnegative Matrix Factorization with the Kullback-Leibler Divergence
Nonnegative Matrix Factorization (NMF) is a fundamental tool in unsupervised learning, which approximates a nonnegative matrix by the product of two low-rank nonnegative factors. The Kullback-Leibler (KL) divergence is best suited to measure the data to model discrepancy when the decomposed data sam…
Damien Lesens, Jérémy E. Cohen, Bora Uçar · 📄 PDF
Plausible Deniability Guarantees for Whistleblowers
Whistleblowers are a key safeguard against organizational wrongdoing, but the threat of retaliation deters reporting. Existing whistleblower-protection proposals lack formal privacy guarantees, and existing differential privacy mechanisms do not directly target the natural threat model -- one in whi…
Leo Richter, Matt J. Kusner · 📄 PDF
VAIOM: Continuous-Input, Discrete-Output Decoder-Only Financial Sequence Modeling
Financial observations are continuous, heterogeneous, and noisy, whereas decoder-only next-token models are usually built around discrete symbolic inputs. We introduce Vector-Input Autoregressive Inference for Ordinal-Return Modeling (VAIOM), a decoder-only Transformer for probabilistic next-return …
Yiming Ma, Xinyu Chen · 📄 PDF
A novel unsupervised machine learning strategy to handle multimodal cardiac PET/MRI data
Arrhythmogenic left ventricular cardiomyopathy is a genetic myocardial disease difficult to diagnose due to the lack of gold standard criteria. Simultaneous PET/MR imaging, combined with multiparametric quantitative analysis, could facilitate the identification of different profiles related to the p…
Brunnhilde Ponsi, Thomas Carlier, Lara Marteau, Aurélien Monnet, Thomas Eugène, Jean-Michel Serfaty, Nicolas Piriou, Hat… · 📄 PDF
Beyond the $d^{2.5}$-mixing bound for Dikin walks on polytopes
Inspired by interior-point methods (IPM) for structured convex optimization, Kannan and Narayanan introduced the Dikin walk for sampling uniformly from polytopes in 2009. As in IPMs, the Dikin walk is affine-invariant, and its convergence is governed by the barrier geometry used to define its local …
Yunbum Kook · 📄 PDF
Multimodal Empirical Bayes Variational Autoencoders for Joint Longitudinal and Time-to-Event Modeling
Longitudinal tumor measurements, dropout information, and genetic covariates provide complementary information about treatment response, but integrating these data sources within a single population modeling framework remains challenging. We extend the empirical Bayes variational autoencoder (EB-VAE…
Anders Sjöberg, Nils Olsson, Marcus Baaz, Mats Jirstrand · 📄 PDF
TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents
Multi-turn agents solve complex tasks through extended sequences of tool interactions before producing a final answer, making credit assignment a fundamental challenge during post-training. Outcome rewards provide reliable supervision for short-horizon reasoning, but become sparse and high-variance …
Leitian Tao, Baolin Peng, Wenlin Yao, Tao Ge, Hao Cheng, Mike Hang Wang, Jianfeng Gao, Sharon Li · 📄 PDF
Lyapunov Exponent as Physics-Informed Dense Reward: RL Discovery of Stabilization Beyond the Kapitza Pendulum
We suggest using the Lyapunov characteristic exponent (LCE) as a dense reward signal for the reinforcement learning problem of stabilizing the inverted pendulum with vertical motion. With LCE, the agent not only successfully found the oscillatory motion known as the Kapitza pendulum but also damped …
Slava Andrejev · 📄 PDF
Lighthouse RL: Sample-Efficient Circuit Optimization via Strategic Reset Points
In this paper, we introduce Lighthouse RL, a sample-efficient reinforcement learning (RL) approach for analog circuit sizing. Traditional methods lack generalization across different performance targets, while standard RL approaches waste resources exploring unpromising regions. Our method addresses…
Mustafa Emre Gürsoy, Stefan Uhlich, Ryoga Matsuo, Yağız Gençer, Arun Venkitaraman, Chia-Yu Hsieh, Andrea Bonetti, Eisaku… · 📄 PDF
Screening of Biosecurity Features in Metagenomic Data with Evo 2 Probes
Genomic foundation models such as Evo 2 learn rich sequence representations, but their value for biosecurity screening is largely unexplored. We ask how much biosecurity-relevant signal is linearly accessible in these representations by training minimal linear and attention probes on frozen Evo 2 la…
Jeremy Guntoro, Alexander Dack, Dylan Danno, Michaela Jančovičová, Križan Jurinović, Vanessa Smilansky · 📄 PDF
MetaPerch: Learning from metadata for bioacoustics foundation models
Bioacoustic foundation models rely on large-scale citizen science platforms like Xeno-Canto for geographically and ecologically diverse data. Recent work has shown that supervision alone can produce SotA species detection models when trained on this large-scale data -- however, there remains unutili…
Mustafa Chasmai, Vincent Dumoulin, Jenny Hamer · 📄 PDF
Linear Independent Component Analysis via Optimal Transport
Linear Independent Component Analysis (ICA) recovers jointly independent source signals from their linear mixtures. To achieve this, classical ICA algorithms attempt to maximize non-Gaussianity, measured by negentropy, which is linked to independence by information theory. Because exact negentropy o…
Ashutosh Jha, Michel Besserve, Simon Buchholz · 📄 PDF
Leveraging unlabelled data for generalizable neural population decoding
Robust and accurate neural decoders are integral to neurotechnologies such as brain-computer interfaces and closed-loop experiments. Recent work has shown that tokenizing neural data at the spike level facilitates multi-session pretraining and delivers state-of-the-art decoding performance. However,…
Ximeng Mao, Nanda H. Krishna, Avery Hee-Woon Ryoo, Matthew G. Perich, Guillaume Lajoie · 📄 PDF
NodeImport: Imbalanced Node Classification with Node Importance Assessment
In real-world applications, node classification on graphs often faces the challenge of class imbalance, where majority classes dominate training, resulting in biased model performance. Traditional GNNs often struggle in such scenarios, as they tend to overfit to majority classes while underrepresent…
Nan Chen, Zemin Liu, Bryan Hooi, Bingsheng He, Jun Hu, Jia Chen · 📄 PDF
AI-Augmented Human Resource Management? Insights from German companies
This study examines the integration of AI into Human Resource Management in German companies. We ask if and how AI-based technologies are \enquote{augmenting} human resource management. Organisations employ generative AI or predictive analytics to transform traditional human resource functions, to s…
Yannick Kalff, Katharina Simbeck · 📄 PDF
Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild
Human-object interaction detection (HOID) has traditionally been formulated as a supervised detection problem over predefined interaction categories. While such paradigms achieve strong performance on closed-set benchmarks, they fundamentally entangle interaction understanding with dataset-specific …
Ting Lei, Jialin Liu, Zhu Xu, Yuxin Peng, Yang Liu · 📄 PDF
Verifying formulas for interventional distributions
We formalize verification in causal graphical models: deciding whether a given observational formula identifies a target interventional distribution. This opens a problem complementary to identification, asking not whether any identifying formula exists, but whether the given formula is identifying.…
Francesco Freni, Leonard Henckel, Sebastian Weichwald · 📄 PDF
Experience Memory Graph: One-Shot Error Correction for Agents
Large Language Model (LLM) agents have shown remarkable capabilities in autonomous decision-making by generating sequential trajectories of states, actions, and observations. However, in complex, long-horizon tasks, these agents frequently suffer from compounding errors and struggle to recover from …
Wenjun Wang, Yuchen Fang, Fengrui Liu, Zibo Liang, Kai Zheng · 📄 PDF
AIMO Interpretability Challenge
We propose the AIMO Interpretability Challenge, a competition on distinguishing robust from spurious reasoning in frontier mathematical language models based on the models' internal mechanisms. The challenge is motivated by a central limitation of standard reasoning benchmarks: strong final-answer a…
Michal Štefánik, Philipp Mondorf, Andreas Waldis, Qianying Liu, Chuan Yang, Michal Spiegel, Josef Kuchař, Marek Kadlčík,… · 📄 PDF
Partially Correlated Verifier Cascades in LLM Harnesses: Concave Log-Odds, Polynomial Reliability, and Blind-Spot Ceilings
Serial verification gates are a core reliability primitive in LLM harnesses: a candidate answer is returned only if $k$ verifier calls all accept it. Under conditionally independent gates, the recent Odds Law (arXiv:2606.15712) shows that posterior log-odds grow linearly in $k$, so failure decays ex…
Jiangang Han · 📄 PDF
Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code
Languages with rich static semantics, such as Rust, provide stronger guarantees for AI-generated code, but their strictness makes generation more difficult. Off-the-shelf compilers can provide useful feedback post-generation, but does not guide intermediate generation steps, such as those during aut…
Niels Mündler-Sasahara, Hristo Venev, Dawn Song, Martin Vechev, Jingxuan He · 📄 PDF
A Self-Evolving Agent for Longitudinal Personal Health Management
Personal health management unfolds over repeated encounters, yet most health AI systems treat each request in isolation. We developed HealthClaw, an open-source agent architecture that updates support as a person's routines, preferences, measurements and risks change. It separates shared safety rule…
Haoran Li, Jiebi Deng, Tong Jin, Jinghong Han, Yuxin Wang, Zexin Wang, Qingyi Si, Weikang Gong, Xiahai Zhuang, Jia You, … · 📄 PDF
Music-to-Dance Generation via Atomic Movements
Music-driven dance generation aims to produce human motion that is both rhythmically synchronized and semantically consistent with music. While recent neural approaches have achieved impressive visual realism, they typically model motion as a continuous signal and neglect its compositional nature, m…
Xinhao Cai, Yixuan Sun, Minghang Zheng, Qingchao Chen, Xin Jin, Song-chun Zhu, Yang Liu · 📄 PDF
The Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop (DVM-HALL) Model and the Net Human-Agent Score (NHAS) in Autonomous Commerce
The rapid proliferation of Agentic Artificial Intelligence fundamentally disrupts traditional customer loyalty paradigms. As AI evolves from passive recommendation algorithms to autonomous, goal-directed agents capable of executing purchasing decisions, the conventional understanding of consumer-bra…
Sai Srikanth Madugula, Peplluis Esteva de la Rosa, Daya Shankar · 📄 PDF
Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0
Most reported gains from agent-optimization methods are one-shot: an agent is optimized against a fixed benchmark and the resulting improvement is reported as if it were a stable property of the method. This does not test the setting that matters for deployed agents, where optimization is applied re…
Wenxiao Wang, Priyatham Kattakinda, Soheil Feizi · 📄 PDF
Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation
Penetration testing traditionally evaluates whether adversaries can exploit weaknesses in software, infrastructure, configurations, or operational controls to achieve security-relevant compromise. This paradigm remains necessary for AI-enabled systems, but it is no longer sufficient. In such systems…
Mohammad Allahbakhsh, Mohammad Hassan Bahari, Moslem Attar-Raouf · 📄 PDF
Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth
We investigate how each component of the Transformer feedforward block architecture design determines how much rank survives across depth at initialization. We reinterpret skip connections and normalization, long understood as controlling magnitude, as mechanisms for preserving gradient rank across …
Katie Everett · 📄 PDF
Improving Wind and Solar Power Prediction with Efficient Wrapper-based Feature Selection: An Empirical Study
With rising global energy demand and growing awareness of climate change and its impacts, the share of renewable energies in the global energy mix continues to grow. Unlike conventional power generation, the output of renewable energy sources cannot be controlled as consistently due to their depende…
Daniel Grillmeyer, Marius Hadry, Michael Stenger, Vanessa Borst, Veronika Lesch, Samuel Kounev · 📄 PDF
Early Adoption of Agentic Coding Tools by GitHub Projects
Agentic coding tools are increasingly capable of generating and submitting pull requests (PRs) to software projects, introducing new forms of human-agent collaboration in software development. While prior studies have examined PR-level outcomes of agent-generated contributions, less is known about h…
Maliha Noushin Raida, Daqing Hou · 📄 PDF
Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study
Historical Manchu OCR must accommodate various visually distinct writing styles, including regular script, running script, and the semi-cursive chancery hand used in palace memorials, despite limited labeled data. We study a multi-expert system that reuses checkpoints from an iterative fine-tuning p…
Zhan Chen, Jiqiao Ma, Chih-wen Kuo · 📄 PDF
AI-accelerated End-to-End Framework for Rapid Professional Upskilling
By 2030, 59 of every 100 workers will need reskilling or upskilling, yet the average time to close an enterprise skills gap grew from roughly 3 days in 2014 to 36 days in 2018. Most current frameworks accelerate single stages of upskilling programs and generally lack industry validation. We present …
Tam Nguyen, Hung Nguyen, Robert Ogburn · 📄 PDF
Earthquaker-AI: A Retrieval-Augmented Generation Framework with Rubric-Based Assessment for Primary School Earthquake Education
This paper presents Earthquaker-AI, a hybrid educational framework building upon a previously implemented educational robotics project by integrating a conversational AI assistant based on Retrieval-Augmented Generation. It aims to enhance earthquake preparedness and conscious action among primary-s…
Xanthi Kokkinou, Chaido Mizeli, Nafsika Koulaxidou, Marina Delianidi, Konstantinos Diamantaras · 📄 PDF
Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models
The emergence of Chain-of-Thought (CoT) reasoning has significantly enhanced the ability of large language models (LLMs) to tackle complex, multi-step tasks. However, when errors occur, current interaction approaches typically involve re-generating another response that may make mistakes again, or u…
Hefeng Zhou, Jinxuan Zhang, Jiong Lou, Yuxin Liu, Chaochao Lu, Jingjing Qu, Jie Li · 📄 PDF
Forecasting Inflation with Microdata: An Adaptive Machine Learning Approach
Does microeconomic heterogeneity help to forecast aggregate inflation in a non-stationary environment? We develop a scan test for whether one forecast outperforms another, over an interval with unknown starting point and duration. To exploit any occasional forecasting power that the scan test detect…
Catherine Chen, Chen Gao, Jonathon Hazell, Lihua Lei, Chen Lian · 📄 PDF
Beyond Consistent Scenarios: Deriving Indirect Influence, Transition Resistance, and Adjustment Dynamics
Assessments of structural change and economic transition dynamics, such as those arising in the energy transition, depend on internally consistent qualitative scenarios specifying the policy environment, technology mix, governance arrangements, and demand conditions. Cross-Impact Balance (CIB) analy…
Andrew G. Ross, Julia Gershenzon, Andreas Kleefeld · 📄 PDF
Shared Bidding Algorithms and Competition: Evidence from Electricity Markets
Competing firms increasingly delegate pricing and bidding decisions to algorithms supplied by the same third-party providers. We study whether a shared algorithm leads competitors to internalise one another's profits, using data from the Australian National Electricity Market, where every battery's …
Nicolas Eschenbaum · 📄 PDF
Selective avoidance of multiple line-of-sight obstacles at 130~m using locally bending space-time wave packets
Self-accelerating optical beams follow curved trajectories rather than propagating rectilinearly, which raises the prospect for avoiding line-of-sight (LoS) obstacles blocking the beam path. However, if a conventional laser beam is intercepted by an obstacle en route to an intended LoS target, then …
Layton A. Hall, Murat Yessenov, Isabelle Lebron, Ayman F. Abouraddy · 📄 PDF
Peak-Decomposition-Free Inverse Metrology of Hyperspectral Moiré Photoluminescence
Hyperspectral photoluminescence (PL) of moiré transition-metal dichalcogenide heterobilayers encodes spatially varying exciton landscapes, but extracting that information is hampered by the ambiguity of multi-peak spectral decomposition. Here we develop a peak-decomposition-free inverse framework fo…
Katsunori Wakabayashi · 📄 PDF
Space-Time Modulated vs 2-Bit Reflect-Arrays: A Comparison of Main Beam Gain and Sidelobe Level Performance
This paper presents a comprehensive analysis of the phase errors introduced by 2-bit reflectarray architectures and investigates their impact on aperture synthesis for beam-steering applications. Building upon this analysis, an amplitude-aware synthesis technique based on space-time modulated (STM) …
Muhammad Rizwan Akram, Douglas H. Werner · 📄 PDF
Quantized Photocurrents in Gapless Topological Matter
The quantum Hall effect in gapped systems represents a defining signature of nontrivial topology. Realizing this principle in gapless matter has remained a central challenge in quantum materials. Chiral topological semimetals provide a unique platform to achieve this aim via symmetry-protected multi…
Byunghoon Kim, Tenzin Norden, Mohammad Yahyavi, Kaustuv Manna, Tyler A. Cochran, Zi-Jia Cheng, Xian P. Yang, Yu-Xiao Jia… · 📄 PDF
Direct Observation of Nanoscale Chiral Light-Matter Interactions Governed by Optical Chirality
Optical chirality has been proposed as the fundamental quantity governing chiral light-matter interactions, but direct experimental verification has remained elusive. Here we realize an optical field with spatially modulated optical chirality and nearly uniform electric energy density, and provide t…
Atsushi Kamegaya Shun Hashiyada, Yoshito Y. Tanaka · 📄 PDF
Constructing mode-resolved quantum optical models for emitters in photonic crystals
Recent advances are enabling quantum emitters to interact with photonic crystals, whose electromagnetic modes exhibit complex dispersion relations, spatial mode structure, and polarization textures. However, modeling light-matter behavior in these systems faces a persistent trade-off: electromagneti…
Antonio Morales-Pérez, Iñaki García-Elcano, Chiara Devescovi, Maia G. Vergniory, Aitzol García-Etxarri, Alejandro Gonzál… · 📄 PDF
Nanoparticle Arrays for Efficient Organic Light-Emitting Diode Emission Management
OLEDs are increasingly applied in illumination and displays because they offer excellent color quality, are mechanically flexible, and are self-emissive. However, their usage is limited by low external quantum efficiency (EQE) and efficiency roll-off at high driving voltages. These limitations, toge…
Aron J. J. Dahlberg, Matas Gužauskas, Malek Mahmoudi, Joel Lehikoinen, Dmytro Volyniuk, Manish Kumar, Anton Matthijs Ber… · 📄 PDF
Quantum metrology with undetected mid-infrared photons for applied non-destructive testing
Metrology with undetected photons is an emerging technique that leverages quantum effects and photon correlations (entanglement) to retrieve valuable information in a target spectral range (e.g., mid-infrared, mid-IR) using measurements in an easily accessible domain (e.g., visible, near-IR). The un…
Paul Gattinger, Andreas W. Schell, Maja Buchegger, Markus Brandstetter, Ivan Zorin · 📄 PDF
Collective-State Preparation in a Subwavelength Triangular Trimer Using SUPER Excitation
The Swing-UP of quantum EmitteR population (SUPER) scheme has recently been proposed as a deterministic method for the preparation of collective radiative states in two strongly dipole-coupled quantum emitters (Phys. Rev. Res. \textbf{8}, 013179 (2026)). Here, we extend this approach to an equilater…
Thomas Nunner, Johannes Kerber, Helmut Ritsch, Arpita Pal · 📄 PDF
Twist Engineering for Reconfigurable Optical and Optoelectronic Devices
Reconfigurable optical and optoelectronic devices require compact tuning mechanisms capable of reshaping electronic, excitonic, polaritonic, and photonic responses without rebuilding the underlying nanostructure. Against this backdrop, twist has emerged as a powerful geometric degree of freedom that…
Gang Huang, Annan Helian, Mengting Jiang, Chi Wang, Yu Xing, Mayank Joshi, Jae Yeong Lee, Jiang Wang, Syed M Assad, Ping… · 📄 PDF
Symmetry-Informed Deep Learning for Electromagnetic Scattering
Deep learning can accelerate the modeling of electromagnetic devices by replacing costly simulations with neural networks trained to map design parameters to scattering parameters. However, data efficiency remains a central bottleneck, as training data is typically generated through expensive numeri…
Viktor A. Lilja, Philippe Tassin · 📄 PDF
End-to-End Quantum Key Distribution Across Hybrid Fiber and Free-Space Links with All-Optical Encoding Conversion
Quantum key distribution (QKD) promises information-theoretically secure communication, but future networks must bridge fiber and free-space links that naturally employ different photonic encodings, namely time-bin in fiber and polarization in free space. Here we demonstrate a complete hybrid fiber …
Khen Cohen, Tomer Nahum, Michael Tzukran, Paz Or, Yehuda Pilnyak, Nitzan Livneh, Hagai Eisenberg, Yaron Oz, Haim Suchows… · 📄 PDF
Phase Angle and Effective Second-Harmonic Generation Coefficient in Uniaxial Crystal
In this paper, the calculation formulae of phase angle are given for two classes of largest effective SHG coefficients in uniaxial crystals by means of the optimization theory. With the help of such calculation formulae, we present the best phase angles and azimuth angles of all uniaxial crystals cl…
Yisheng Song · 📄 PDF
Optimal photostimulation selection for iterative activity maps
All-optical two-photon holographic optogenetics enables causal circuit mapping by stimulating defined neurons or ensembles while imaging population activity. Yet exhaustive connectivity mapping remains experimentally prohibitive because of combinatorial complexity, tissue heating, photodamage, and e…
Jacob J. Morra, Kaitlyn E. Fouke, Owen Traubert, Eva A. Naumann · 📄 PDF
QUBO-Optimized Evidence Selection for Retrieval-Augmented Question Answering with Unconventional Solvers
Retrieval-augmented question answering depends on selecting evidence passages that jointly support answer generation. However, many RAG pipelines rely on top-\(k\) ranking, where passages are selected mainly by individual relevance scores, even though multi-hop questions often require complementary …
Rahul Singh, Madhav Vadlamani · 📄 PDF
Evaluating Health Misinformation in Low-Resource Languages: Integrating Small Language Models with a Culturally-Sensitive Responsible NLP Framework (Bangla as a Case Study)
Artificial Intelligence (AI) technologies, while serving as a foundational enabler for modern social media and digital health services, exert a bivalent effect by simultaneously acting as a combatant against and a spread vector for misinformation. A prevalent challenge in mitigating this issue arise…
Farnaz Farid, Raihan Alam, Al Al-Areqi, Farhad Ahamed, Muhammad Hassan Khan, Sadia Hossain, Irena Veljanova, Anika Tabas… · 📄 PDF
Agentic Service-Oriented Computing: A Manifesto for the Next Frontier of Service-Oriented Computing
The rapid emergence of LLM-powered autonomous and semi-autonomous agents is reshaping software systems from static, request-response components into goal-directed, adaptive, and tool-using computational actors. As these agents move from isolated cognitive prototypes into complex distributed workflow…
Amin Beheshti, Rong N. Chang, Boualem Benatallah, Fabio Casati, Schahram Dustdar, Geoffrey Fox, Quan Z. Sheng, Yan Wang,… · 📄 PDF
When Close Enough Is Not Enough: Autoregressive Drift in Quantum Circuit Synthesis
Quantum circuit optimization for fault-tolerant computing requires exact functional equivalence while minimizing expensive non-Clifford resources such as T gates. We study this problem using a compact 44.8M-parameter encoder-decoder transformer with structured circuit tokenization, evaluating on par…
Mehdi Saeedi, Eddie Richter, Paul Hartke · 📄 PDF
Detecting Phishing in Ethereum Networks using Quantum Machine Learning
This article explores the potential of Quantum Machine Learning (QML), specifically assessing a Quantum Support Vector Machine (QSVM) and a Variational Quantum Classifier (VQC) for detecting anomalies in real-world financial transaction data. While these QML methods outperform statistical methods, t…
Sai Sakunthala Guddanti, Anupama Ray, Mrunal Arun Kumavat, Anil Prabhakar · 📄 PDF
A Comparative Analysis of Ising Formulations for Neuromorphic Maximum-Likelihood Channel Decoding
Neuromorphic computing has so far been driven predominantly by machine-learning workloads, yet its underlying properties also make it particularly well suited to combinatorial optimization problems expressed in Ising or QUBO form. While neuromorphic Ising solvers have been demonstrated, how a given …
George N. Katsaros, Morgan Sabine, Konstantinos Nikitopoulos · 📄 PDF
ORRAM: An OpenROAD-Integrated RAM Generator Using Standard Cells
Memory inference remains a significant challenge in turnkey ASIC design flows. Inferring flip-flops from RTL can create thousands of densely interconnected instances which dramatically slow down design flows and impede performance. Memory compilers address this issue, although they are third-party t…
Brayden Louie, Thinh P. Nguyen, Matt Liberty, Austin Rovinski · 📄 PDF
Emulated Integrity Replica: Enabling Self-Healing on FPGA SoCs via Hierarchical Twins
Convolutional neural networks (CNNs) are increasingly being deployed on system-on-chip (SoC) platforms, where hardware-accelerated inference enables low-latency edge computing. Achieving fault tolerance on these devices remains challenging because conventional redundancy (dual/triple modular redunda…
Arsalan Ali Malik, Ali Suvizi, Guru Venkataramani, Aydin Aysu · 📄 PDF
ArchSim: Computer Architecture Simulation as a Service
Conducting a complete computer architecture simulation study is challenging because configuration, execution, and analysis are often encoded implicitly in scripts or directory conventions rather than represented explicitly. As a result, studies are difficult to scale, hard to reproduce, and dependen…
Sabila Al Jannat, Wenhan Lyu, Le Khanh Trinh Mai, Huizhi Zhao, Zhuoyan Zheng, Katherine E. Isaacs, Yifan Sun · 📄 PDF
Realizable N:M Sparse Transformer Inference via Search-Kernel Co-Design
Vision Transformers (ViTs) achieve strong accuracy but incur high inference latency. Semi-structured N:M sparsity can reduce arithmetic cost, yet its theoretical savings often fail to translate into proportional end-to-end speedups on modern GPUs. This mismatch arises because deployment latency depe…
Yiming Liu, Wenqi Lou, Zhiguang Wang, Zhiwei Ke, Fengrui Zuo, Chao Wang, Xuehai Zhou · 📄 PDF
CLIP-3D: Closed-Loop Evaluation of Performance and Physical Constraints for 3D ICs
3D integration packs more power into a smaller footprint, so a candidate design's actual throughput depends on its layout: which macro sits on which tier, where the hot spot lands, and how cache geometry maps to access cycles. Architectural simulators like gem5 report IPC under idealized timing. The…
Shuo Ren, Libo Shen, Yaohui Han, Leilei Jin, Chenghan Wang, Zhen Zhuang, Rongliang Fu, Bei Yu, Tsung-Yi Ho · 📄 PDF
HeteroMosaic: Exposing and Exploiting Heterogeneous Execution Opportunities for Energy-Efficient Edge LLM Inference
Modern edge system-on-chips (SoCs) combine CPUs, integrated GPUs (iGPUs), and neural processing units (NPUs), yet existing LLM runtimes typically make coarse device-level decisions or optimize operators in isolation. As a result, they underutilize heterogeneous resources, particularly on unified-mem…
Gregory Hyegang Jun, Wesley Pang, Eddie Richter, Mehdi Saeedi, Aporva Amarnath, Pallavi Ferrao, Deming Chen · 📄 PDF
A 32-channel event-based bio-signal analog front-end with adaptive delta and pulse frequency encoding
Low-power event-based Analog Front-Ends (AFEs) are essential for building efficient, end-to-end neuromorphic signal processing systems. In this paper, we present an event-based AFE Application-Specific Integrated Circuit (ASIC) optimized for biomedical signal acquisition and encoding. The chip featu…
Narayanan Shyam, Saptarshi Ghosh, Giacomo Indiveri · 📄 PDF
Mind the Gap: Promises and Pitfalls of Hierarchical Planning in LeWorldModel
We investigate whether temporal hierarchy can improve LeWorldModel on long-horizon goal-conditioned control. We introduce Hi-LeWM, an extension that freezes the pretrained low-level LeWM and adds high-level planning over latent subgoals. We evaluate Hi-LeWM on PushT and Cube across increasing goal o…
Niccolò Caselli, Salvatore Lo Sardo, Francesco Massafra, Ippokratis Pantelidis, Samuele Punzo, Sathya Kamesh Bhethanabho… · 📄 PDF
TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors
Vision-Language-Action (VLA) models are deployed through pipelines that end users cannot audit, and a poisoned VLA can behave normally on clean observations while a small visual trigger redirects a long-horizon robot policy before any failure becomes observable. Existing vision or language defenses …
Pinhan Fu, Xianda Guo, Xuetao Li, Wenke Huang, Ruilin Wang, Weiheng Zhao, Wei Sui, Mang Ye · 📄 PDF
Improving Autonomous Nano-drones Performance via Automated End-to-End Optimization and Deployment of DNNs
The evolution of energy-efficient ultra-low-power (ULP) parallel processors and the diffusion of convolutional neural networks (CNNs) are fueling the advent of autonomous driving nano-sized unmanned aerial vehicles (UAVs). These sub-10 cm robotic platforms are envisioned as next-generation ubiquitou…
Vlad Niculescu, Lorenzo Lamberti, Francesco Conti, Luca Benini, Daniele Palossi · 📄 PDF
Streamlining stereo differentiable rendering for marker-free real-time tracking of surgical robots
Purpose: Marker-based tracking of surgical robots is occlusion-prone in cluttered operating rooms. We evaluate stereo differentiable rendering for marker-free, real-time robot pose tracking, potentially improving safety, reducing setup time, and enabling multi-robot interaction. Methods: We extend t…
Yanghe Hao, Martin Huber, Christos Bergeles, Tom Vercauteren · 📄 PDF
Instance-Enriched Semantic Maps for Visual Language Navigation
Visual Language Navigation (VLN) aims to enable an embodied agent to navigate complex environments by following natural language instructions. Recent approaches build semantic spatial maps and leverage Large Language Models (LLMs) for reasoning and decision making. Despite these advances, existing s…
Jiho Hong, Eunae Kang, Sanghyun Kim, Young-Sik Shin · 📄 PDF
Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference
Vision-Language-Action (VLA) models have achieved impressive performance on diverse embodied tasks. However, deploying VLA models on low-power onboard devices, such as the Jetson Orin, remains challenging due to their high computational complexity, which leads to substantial inference latency and lo…
Zebin Yang, Qi Wang, Yunhe Wang, Xiurui Guo, Bo Yu, Shaoshan Liu, Jiafeng Xu, Hao Dong, Meng Li · 📄 PDF
Vision-Based Dribbling for Humanoid Soccer via Privileged Representation Learning
Recent advances in humanoid robotics have highlighted the importance of deployable loco-manipulation skills. Dribbling a soccer ball while evading active opponents requires simultaneous balance, precise ball control, and awareness of a dynamic adversary under onboard sensing and real-time constraint…
Flavio Maiorana, Valerio Spagnoli, Eugenio Bugli, Flavio Volpi, Daniele Affinita, Vincenzo Suriani, Daniele Nardi, Luca … · 📄 PDF
Globalized Constrained Stein Variational Inference for Diverse Feasible Robot Motion Planning
Robot motion planning is inherently multimodal, yet classical planners typically return only a single solution. Probabilistic formulations address this limitation by maintaining a distribution over motions, allowing the planner to reason over multiple low-cost alternatives. In robotics, however, mot…
Jiayun Li, Georgia Chalvatzaki · 📄 PDF
Practical Judgment, Virtue, and Intuition in the Use of Opaque AI-Enabled Systems
AI-enabled systems are seeing increasing deployment across numerous domains, with many being "black boxes" with respect to core functions and capabilities. I.e., many systems take inputs and give outputs, but without users having any ability to see how the former lead to the latter. AI-enabled syste…
Nathan G. Wood, Andrew P. Rebera · 📄 PDF
Directional Constraints for Efficient Exploration in Safe Reinforcement Learning
Reinforcement Learning has revolutionized the landscape of robotic research, allowing robust learning of complex robotic skills in simulation. However, real-world deployment in open-ended environments requires strong safety guarantees to prevent dangerous or harmful behaviors. Safe Reinforcement Lea…
Paolo Magliano, Puze Liu, Jan Peters, Davide Tateo, Raffaello Camoriano · 📄 PDF
Autonomous Tracking and Terminal Guidance of Moving Targets for Fixed-Wing UAVs
This study introduces a unified control framework for fixed-wing unmanned aerial vehicles (UAVs) fitted with a pan-tilt (PT) camera, intended to perform an end-to-end mission spanning from initial target detection to accurate terminal engagement. The proposed system employs a three-phase strategy: a…
Wei-Hao Liou, Teng-Hu Cheng · 📄 PDF
PixelLoop: Shortcut Topological Navigation with Pixel-Level Loops
Although topological mapping and navigation have been studied extensively, the specific role and downstream effect of loop closures in purely topological representations has received relatively little attention. Importantly, loop closure over topological maps is distinct from loop closure over globa…
Sarthak Chittawar, Vansh Garg, Aditya Vadali, Krish Pandya, Rohit Jayanti, Sourav Garg, Madhava Krishna · 📄 PDF
ExToken: Structured Exploration for Efficient Vision-Language-Action Reinforcement Fine-tuning
Reinforcement Learning (RL) has demonstrated significant potential for improving Vision-Language-Action (VLA) models on complex manipulation tasks. However, its practical scalability remains severely limited by the substantial cost of environmental interactions. In this work, we first investigate th…
Yilun Kong, Yunpeng Qing, Guozheng Ma, Haoyu Wang, Li Shen, Zhi Hou, Dacheng Tao · 📄 PDF
MAMMOTH: A Multi-Modal End-to-End Policy for Off-Road Mobility Robust to Missing Modality
Reliable autonomous navigation in unstructured off-road environments remains a critical unsolved challenge due to extreme terrain diversity, drastic illumination variations and acute sensor degradation. Recent developments have approached the problem as a traversability costmap estimation or visual …
Ahaan Kotian, Shivani Subramanyan, Suresh Sundaram · 📄 PDF
ChunkFlow: Towards Continuity-Consistent Chunked Policy Learning
Vision-language action (VLA) models increasingly adopt chunked action heads to satisfy real-time constraints; however, this introduces boundary jitter: overlapping regions between consecutive chunks often yield inconsistent predictions, degrading temporal coherence and the task success rate. Existin…
Zhao Yang, Yinan Shi, Mingyuan Yao, Wenyao Xue, Yawei Jueluo, Longjun Liu · 📄 PDF
DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation
Reinforcement learning holds great promise for improving robot policies beyond the limits of imitation learning. However, its practical adoption remains bottlenecked by the lack of reliable vision-language reward models that provide dense and informative feedback. Two key challenges remain: acquirin…
Yu Fang, Wanxi Dong, Jiaqi Liu, Yue Yang, Mingxiao Huo, Yao Mu, Huaxiu Yao, Li Erran Li, Daniel Szafir, Mingyu Ding · 📄 PDF
Breaking Déjà Vu: Independent Auditing of Visual Place Recognition through Vision-Language Reasoning
Visual place recognition (VPR) is a key enabler of accurate localization and long-term autonomous navigation in robotics applications, such as loop closure detection for simultaneous localisation and mapping (SLAM). However, real-world VPR deployment relies on selecting an image matching threshold t…
Sania Waheed, Michael Milford, Sarvapali D. Ramchurn, Shoaib Ehsan · 📄 PDF
AVSCap: Orchestrating Audio-Visual Synergy for Omni-modal Video Captioning
Omni-modal video captioning is not merely combining visual captioning with audio transcription: a useful caption must describe how visual actions, speech, music, and sound effects co-evolve. Existing large multimodal models often fail at this relational step, treating audio and visual streams as loo…
Yanghai Wang, Jiahao Wang, Jiafu Tang, Yuanxing Zhang, Zhe Cao, Hanyan Bian, Zijie Zhang, Weiliang Luo, Zhiyu Pan, Zixua… · 📄 PDF
LARAD: Layout-Aware Road Anomaly Detection via Spatial-Logic Reasoning
Accurate open-world obstacle detection is critical for autonomous driving. Current anomaly segmentation methods suffer from a fundamental blind spot: they over-rely on texture novelty to identify out-of-distribution (OoD) objects while ignoring contextual spatial logic. Furthermore, mitigating the r…
Shiyi Mu, Xujie Chen, Shugong Xu · 📄 PDF
Statistical Non-linear Reconstruction Loss for Image Anomaly Detection
Reconstruction-based methods are a cornerstone of unsupervised image anomaly detection, but they remain vulnerable to \emph{outlier leakage}, where standard mean squared error (MSE) loss drives the model to faithfully reconstruct anomalous patterns. We propose a Non-linear Reconstruction Loss that a…
Nguyen Minh Tri, Hoang Khuong Duy, Huynh Cong Viet Ngu · 📄 PDF
Metric-Guided Synthetic Image Data Rendering for Deep Learning compatible with Agentic AI
Deep learning computer vision for scientific applications requires collecting and annotating large datasets in a laborious, expensive and error-prone process. Synthetic data generation through 3D modelling and rendering may simplify this process and increase the accuracy of annotations by generating…
Martina Radoynova, Samuel Pantze, Trina De, Ulrik Günther, Artur Yakimovich · 📄 PDF
Inhibited Self-Attention: Sharpening Focus in Vision Transformers
Vision Transformers (ViTs) have demonstrated remarkable performance in computer vision tasks. However, their self-attention mechanism often diffuses focus across background regions, relying on spurious correlations rather than object-relevant cues. Inspired by inhibitory mechanisms observed in biolo…
Peter R. D. van der Wal, Nicola Strisciuglio, George Azzopardi · 📄 PDF
Hy-Embodied-VLM-1.0: Efficient Physical-World Agents
Building capable embodied agents requires not only multimodal perception and understanding, but also agentic capabilities for reasoning about actions, adapting to evolving situations, and interacting with the physical world. In this report, we introduce Hy-Embodied-VLM-1.0, an efficient and powerful…
Ziyi Wang, Xumin Yu, Yongming Rao, Yonggen Ling, Yunheng Li, Oran Wang, Mingqi Gao, Yuchen Zhou, Yves Liang, Zuyan Liu, … · 📄 PDF
UniMedSeg: Unified In-Context Learning for Multi-Paradigm 2D/3D Medical Image Segmentation
Medical image segmentation foundation models are expected to generalize across diverse clinical scenarios, yet existing universal methods remain fragmented by prompt paradigms and spatial dimensions. Visual in-context learning, interactive segmentation, and language-guided segmentation are typically…
Yunzhou Li, Jiesi Hu, Yanwu Yang, Hanyang Peng, Chenfei Ye, Jianfeng Cao, Yixuan Yuan, Ting Ma · 📄 PDF
Rank-1 Identity Consensus Predicts Gallery Enrollment in 1:N Face Matching More Accurately than Score Thresholding
In operational 1:N face identification, a crucial question arises for each probe: is this person enrolled in the gallery or not? The stakes are high and asymmetric. Rejecting a mate-present (MP) probe loses a valid lead; accepting a mate-absent (MA) probe makes every returned candidate a false ident…
Gabriella Pangelinan, Aman Bhatta, Michael C. King, Kevin W. Bowyer · 📄 PDF
Open-KNEAD: Knowledge-grounded Nutrition Estimation via Agentic Decomposition
Multimodal Large Language Models (MLLMs) are increasingly used for dietary assessment from meal images, where retrieval-augmented grounding was shown to sharpen nutrition estimates. However, we find this premise no longer holds for current MLLMs. A modern MLLM's direct estimate now matches or surpas…
Bruce Coburn, Jingbo Yue, Jinge Ma, Siddeshwar Raghavan, Gautham Vinod, Fengqing Zhu · 📄 PDF
Domain-Incremental Remote Sensing Change Detection via Difference-Guided Adaptation and Frequency-Decoupled Distillation
Remote sensing change detection (RSCD) models are prone to catastrophic forgetting when incrementally adapted to new domains. Existing domain-incremental learning (DIL) methods mainly preserve image-level representations but often overlook bitemporal discrepancy cues, which are critical for robust c…
Daifeng Peng, Yaning Li, Haiyan Guan · 📄 PDF
Exact and Calibrated Diffusion Reconstruction for Digital Breast Tomosynthesis
Limited-angle digital breast tomosynthesis (DBT) reconstructs a volume from a few low-dose projections over a narrow arc. At a representative nine-view, $25^{\circ}$ protocol more than 98% of image space is unmeasured, so a learned prior must supply structure in the missing wedge. Conditional diffus…
Imade Bouftini · 📄 PDF
Point Tracking in Surgery--The 2025 Surgical Tattoos in Infrared Challenge (STIRC2025)
Point tracking in surgery is crucial to enable applications in downstream tasks such as segmentation, 3D reconstruction, virtual tissue landmarking, autonomous probe-based scanning, and subtask autonomy. This paper introduces the 2025 iteration of a point tracking challenge to address this, wherein …
Adam Schmidt, Mert Asim Karaoglu, Zijian Wu, Jiaming Zhang, Yuxin Chen, Tim Salcudean, Ho-Gun Ha, Minkang Jang, Kyungmin… · 📄 PDF
ViCo3D: Empowering LiDAR-based Collaborative 3D Object Detection with Vision Foundation Models
LiDAR-based collaborative 3D perception in Vehicle-to-Everything (V2X) systems typically relies on fusing bird's-eye-view (BEV) features across agents. However, current BEV representations, typically extracted by LiDAR backbones trained from scratch, are geometry-dominated and lack general semantic …
Haojie Ren, Songrui Luo, Lingfeng Wang, Yan Xia, Yao Li, Jing Li, Lu Zhang, Jiajun Deng, Yanyong Zhang · 📄 PDF
Controllable Generation of Diverse Dermatological Imagery for Fair and Efficient Malignancy Classification
Accurate dermatological diagnosis naturally necessitates equitable performance across diverse populations, yet a systematic lack of expertly annotated images, especially for underrepresented skin tones and rare diseases, impedes progress toward measurably fair methods. We introduce cgDDI (Controllab…
Héctor Carrión, Narges Norouzi · 📄 PDF
X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras
We present X-lens, a compact feed-forward model for metric depth estimation from a variable number of calibrated fisheye and pinhole views. To support real-time downstream perception, X-lens is built around a geometry-aware heterogeneous camera formulation with two key components. Learnable calibrat…
Heng Zhou, Shuhong Liu, Yonghao He, Bohao Zhang, Fa Fu, Chenhui Hou, Xianbao Hou, Lijun Han, Wei Sui · 📄 PDF
DermDepth: Toward Monocular Metric Scale 3D Reconstruction Models for Dermatology
Dermatological practice routinely involves measuring and tracking lesion size, morphology and texture, as critical components of wound or skin cancer screening, monitoring and diagnosis. To accomplish this task, practitioners often image the skin surface with commonly available off-the-shelf camera …
Héctor Carrión, Narges Norouzi · 📄 PDF
FlowWAM: Optical Flow as a Unified Action Representation for World Action Models
World Action Models (WAMs) are able to leverage pretrained video generators for both world modeling and action prediction. However, directly leveraging such video generators for control raises a new challenge: how to represent actions in a suitable form that aligns with pretrained video generators w…
Yixiang Chen, Peiyan Li, Yuan Xu, Qisen Ma, Jiabing Yang, Kai Wang, Jianhua Yang, Dong An, He Guan, Gaoteng Liu, Jianlou… · 📄 PDF
AVQ-Attention: Adaptive Vector-Quantized Attention
The $\mathcal{O}(N^2)$ complexity of attention over $N$ tokens remains a computational bottleneck in transformer models. Vector-Quantized (VQ) attention reduces this to $\mathcal{O}(MN)$ by representing keys with $M$ codewords, but applies uniform codebook capacity regardless of where attention mass…
Winfried van den dool, Patrick Forré, Amir Habibian, Yuki M. Asano, Max Welling · 📄 PDF
ANGLE: Angular Neural Generative Learning via Engression
Circular data, representing angles or directions, are frequently encountered in computer vision, biology, geology, and meteorology. Traditional regression targets the conditional mean, which is often geometrically misleading for circular responses under multimodal, skewed, or asymmetric data structu…
Rajdeep Pathak, Archi Roy, Tanujit Chakraborty · 📄 PDF
Verifier-Based Reinforcement Fine-Tuning of Reasoning Models for Thermal Energy Storage Control
Buildings are expected to shift cooling loads in response to grid conditions. Thermal energy storage (TES) enables this shift, but scheduling it well requires planning hours ahead under storage constraints. Model predictive control (MPC) and reinforcement learning are difficult to scale across build…
Takumi Shioda, Kohei Terashima, Tatsuo Nagai · 📄 PDF
Toward Localizing and Repairing Bias in Transformer Attention Heads
Transformer language models are increasingly used as software components, yet biased outputs remain difficult to localize and repair inside the model. Existing fairness testing and repair methods largely operate at the input-output or retraining level, while recent work suggests that bias-related be…
Sigma Jahan · 📄 PDF
Deep4ge: DNN Training Trajectories for Fault Detection and Diagnosis
Deep learning systems often fail due to subtle implementation faults that alter training behavior. Recent work has studied how to detect and diagnose such failures from changes observed across training epochs. However, the software engineering community still lacks a public dataset of per-epoch trai…
Sigma Jahan · 📄 PDF
Energy-Based Physics-Informed Form Finding for Clustered Tensegrity Structures
Tensegrity form-finding and physical property prediction are fundamental inverse problems in structural mechanics, which aim to determine equilibrium configurations and internal force distributions. These problems are challenging due to strong nonlinearity arising from the coupling between geometry …
Jing Qin, Muhao Chen · 📄 PDF
Accelerated Mixing Time of Randomized Hamiltonian Monte Carlo
We show the Randomized Hamiltonian Monte Carlo (RHMC) algorithm has accelerated mixing time guarantees for sampling from log-concave probability distributions. RHMC proceeds by repeatedly simulating the continuous-time Hamiltonian dynamics for some random integration times, and resetting the velocit…
Siddharth Mitra, Vishwak Srinivasan, Xiuyuan Wang, Andre Wibisono · 📄 PDF
Contrastive-Collapsed Loss for Flexible and Geometrically Optimal Embeddings and Faster Convergence
In this work, we introduce CoCo, a loss function aimed at learning normalized and well-structured representations. The proposed loss encourages intra-class collapse and inter-class contrast while preserving sufficient flexibility for neural networks to approximate geometrically optimal embeddings wi…
Blanca Cano-Camarero, Ángela Fernández-Pascual, José R. Dorronsoro · 📄 PDF
LatentFlow: A General Framework for Conditioning Stochastic Processes
Stochastic-process models are, as a rule, far easier to simulate than to condition. Non-linear observations, non-Gaussian likelihoods, black-box information, and global constraints all induce intractable conditional laws, requiring bespoke, model-specific constructions. We introduce LatentFlow, a si…
Louis Sharrock, Lachlan Astfalck, Henry Moss · 📄 PDF
Efficient Sequential Calibration with $O(T^{2/3-ε})$ Error Bound
We study the online binary sequential calibration problem. A recent breakthrough by \citet{dagan2024breaking} overcomes the classical \(T^{2/3}\) barrier for calibration error. Building on this result, we present an efficient randomized forecaster that achieves an expected calibration error \(O(T^{2…
Zihan Zhang · 📄 PDF
Robustness of Deep Learning Models for PV Power Forecasting under NWP Forecast Errors: A Spatiotemporal and Physically Interpretable Analysis
Engineering use of AI forecasting models requires not only high nominal accuracy but also predictable behavior under uncertain inputs. In photovoltaic (PV) forecasting, this requirement is especially challenging because numerical weather prediction (NWP) errors are temporally correlated, state depen…
Dandan Chen, Yan Zhao, Xuepeng Chen · 📄 PDF
Ensemble Controlled-Flow Filtering for Implicit Data Assimilation
Data assimilation estimates the state of a dynamical system from model forecasts and incoming observations. Many observation mechanisms, however, are many-to-one, implicit, non-smooth, or accessible only through simulation, and need not provide the residual structures or likelihood guidance required…
Zhuoyuan Li, Yue Zhao, Ming Li · 📄 PDF
Watermark Forensics for Generative Models: An Information-Theoretic Perspective
A watermark in a generative model's output is usually asked only whether a text is machine-made. The same mark can do more: attribute it to the user who produced it, extract a hidden payload, or localize the part that survives editing. These form a forensic ladder, and we ask what each rung costs in…
Xiaoyu Li, Zheng Gao, Xiaoyan Feng, Jiaojiao Jiang, Yulei Sui, Jiankun Hu · 📄 PDF
The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting
A growing family of indices scores how predictable a series is from its spectrum. Practitioners increasingly read these scores as answering a different question: whether \emph{adding context}, a longer lookback, a retrieval plug-in, or a pretrained model, will help. These are not the same question. …
Mert Onur Cakiroglu, Mehmet Dalkilic, Hasan Kurban · 📄 PDF
A Shortcut to Statistically Steady-State Turbulence with Flow Matching
Many nonlinear physical systems exhibit an initial transient phase in which perturbations grow before nonlinear interactions lead to a statistically steady state. While this saturated regime is of primary interest, direct numerical simulations must resolve the full transient dynamics before reaching…
Gianluca Galletti, Gerald Gutenbrunner, William Hornsby, Lorenzo Zanisi, Naomi Carey, Stanislas Pamela, Johannes Brandst… · 📄 PDF
The Seriality Gap in Video Diffusion Models
When one ball strikes another, then another, video models should predict the consequences of each bounce. In controlled experiments on multi-ball hard-sphere dynamics, we find that the performance of standard bidirectional video diffusion degrades as the causal chain lengthens, even when provided mo…
Jorge Diaz Chao, Konpat Preechakul, Yuxi Liu, Yutong Bai · 📄 PDF
Solution of the Hempel's statistical ambiguity problem and Causal AI
This paper addresses Carl Hempel's longstanding problem of statistical ambiguity in inductive-statistical inference, in which contradictory predictions are derived from statistical laws. To avoid such predictions, Carl Hempel proposed the Requirement of Maximal Specificity (RMS) for the statistical …
Evgenii Vityaev · 📄 PDF
Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques
Diffusion large language models (dLLMs) offer a theoretical advantage in parallel generation over standard autoregressive models. However, parallel generation alone does not guarantee practical speedups. Realizing this efficiency requires specialized inference mechanisms, such as diffusion-aware cac…
Daehoon Gwak, Minhyung Lee, Junwoo Park, Jaegul Choo · 📄 PDF
Reproducible Reservoir Computing with Thermally Driven Superparamagnets: Controlling Temperature Sensitivity
Unconventional computing systems must demonstrate robust performance under real-world environmental conditions to enable practical deployments. We have recently proposed superparamagnetic nanodot ensembles driven by strain-induced magnetoelectric coupling as exciting candidates for use as ultra-low …
Zhengfei Chen, Alex Welbourne, Matthew O. A. Ellis, Dan A. Allwood, Eleni Vasilaki, Thomas J. Hayward · 📄 PDF
ChartGenEval: Corruption-Tested Multi-Dimensional Feedback for Rhythm-Game Chart Generation
A generated rhythm-game chart need not reproduce one official note sequence: many note choices can fit the same song and difficulty. Reference-note agreement therefore measures reconstruction, not the full design problem. We introduce ChartGenEval, a six-question evaluation framework with an automat…
Jhen-Ke Lin · 📄 PDF
Unveiling Complex Collective Behaviors from Simple Rewards
Multi-agent Reinforcement Learning (MARL) holds great potential for robot swarms, but the black-box nature of neural policies complicates strategic analysis, limiting multi-robot applications. Furthermore, complex swarm behaviors can surprisingly emerge from simple rewards without explicit aggregati…
Yize Mi, Jianan Li, Liang Li, Shiyu Zhao · 📄 PDF
A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study
Clinical notes contain many of the signs and symptoms that bring patients to care, yet this information rarely reaches structured fields. Existing extraction approaches either rely on context-insensitive rules that generate false positives or on supervised models that require substantial fine-tuning…
Cameron Cagan, Pedram Fard, Jiazi Tian, Jingya Cheng, Shawn N. Murphy, Hossein Estiri · 📄 PDF
UR-VC: Unsupervised Robotic Value Correction for Time-Derived Progress Proxies
Modern robot learning systems increasingly rely on dense progress or value signals to evaluate intermediate states, guide policy learning, and detect task completion, making the quality of these signals critical. Since such dense labels are rarely available at scale, normalized time within a demonst…
Lirui Zhao, Modi Shi, Li Chen, Qi Liu, Ping Luo, Hongyang Li · 📄 PDF
MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations
Long-term memory has become a foundational capability for LLM-based agents that accompany users across extended, multi-session interactions. Existing benchmarks, however, evaluate such memory almost exclusively through downstream question answering, scoring only the correctness of a final answer. Th…
Xixuan Hao, Zeyu Zhang, Zehao Lin, Yihang Sun, Ziliang Guo, Xichong Zhang, Yuxuan Liang, Feiyu Xiong, Zhiyu Li · 📄 PDF
Real-time fall detection based on vision for low-power edge platforms
Falling detection is vital for elderly care and intelligent surveillance; however, prevailing vision-based approaches predominantly frame it as static pose classification or discrete temporal pattern matching, fundamentally overlooking the instability dynamics of the human support system. This paper…
Wenjun Xia, Zhicheng Peng, Haopeng Li, Zhengdi Zhang · 📄 PDF
Knowledge- and Gradient-Guided Reinforcement Learning for Parametrized Action Markov Decision Processes
In this paper, we study Reinforcement Learning in Parametrized Action Markov Decision Processes (PAMDP), where each decision consists of a symbolic action and numerical parameters. In such settings Reinforcement Learning algorithms typically determine parameters with one-shot estimators, which makes…
Jonas Ehrhardt, René Heesch, Oliver Niggemann · 📄 PDF
ViHoRec: A Quality-Controlled Vietnamese Hotel Recommendation Dataset and Cold-Start Benchmark
Recommender-system research for Vietnamese remains limited by the absence of a public, well-documented hotel interaction resource. Building such a resource is challenging for three reasons: cross-platform hotel names must be reconciled before interactions are comparable; quality must be audited with…
Minh Hoang Nguyen · 📄 PDF
Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models
Frozen small code LLMs are deployed locally, yet the information guiding a retry after a failed attempt is still measured without placebo controls in the self-repair literature. We treat a failed program as a conjecture and an execution counterexample as an oracle-relative refutation, and introduce …
Mehmet Iscan · 📄 PDF
FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem Generation
Math reasoning has achieved significant progress with the rapid advancement of Multimodal Large Language Models (MLLMs), however analytic geometry remains largely underexplored, primarily due to the scarcity of annotated samples. Existing diagram generation approaches struggle with analytic geometry…
Ruoran Xu, Wending Gao, Qiufeng Wang · 📄 PDF
Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs
Aligned language models routinely misreport under non-evidential incentive pressure: they agree with a confident user or overstate certainty even when their internal belief is unchanged. We cast this as a failure of internal incentive-compatibility (IC) and present a method for learning and certifyi…
Sen Yang, Yuen-Hei Yeung · 📄 PDF
Win by Silence: Deletion Non-Monotonicity, Autonomous Exploitation, and Typed-State Gating in LLM Plan Evaluation
Plan evaluators can reward a strategic plan for becoming less explicit. This paper studies that failure in a staged expected-value scorer for LLM-generated venture routes. Proposition 1 gives the score change from deleting an interior transition while retargeting its predecessor and retaining downst…
Aleh Manchuliantsau · 📄 PDF
Dynamic Resource Allocation for Ensemble Determinization MCTS
Simulation-based algorithms are especially suited for high-uncertainty environments such as adversarial board games with significant elements of randomness and hidden information. In particular, several Monte Carlo Tree Search (MCTS) variants are commonly used in such domains. In this paper, we prop…
Jakub Kowalski, Adam Ciężkowski, Artur Krzyżyński, Mark H. M. Winands · 📄 PDF
Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model
Automatic speech recognition is dominated by autoregressive decoders that emit one token at a time. We ask whether a discrete diffusion language model can transcribe speech instead, refining a whole transcript in parallel over a small number of denoising steps. We train an audio-native interface for…
Harsha Vardhan Khurdula, Abhinav Kumar Singh, Yoeven D Khemlani, Vineet Agarwal · 📄 PDF
PalmClaw: A Native On-Device Agent Framework for Mobile Phones
Large Language Model (LLM) agents have moved beyond generating responses to executing multi-step tasks by calling tools, observing the results, and iteratively deciding the next action. Most agent systems run on desktops or servers, which support tool use and task automation. Mobile devices are also…
Hongru Cai, Yongqi Li, Ran Wei, Wenjie Li · 📄 PDF
TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale
Training robust autonomous driving agents requires a simulator that is fast enough for reinforcement learning at scale, realistic enough to ground behavior in real-world map structure, and diverse enough to cover the safety-critical long tail that logged data rarely contains. We present TerraZero, a…
Zhouchonghao Wu, Akshay Rangesh, Weixin Li, Wei-Jer Chang, Zachary Lee, Tim Wang, Wei Zhan · 📄 PDF
Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution
Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires. They often follow a maximum-context-first strategy--re-reading files and dependencies they have already seen--turning a one-line edi…
Junjie Yin, Xinyu Feng · 📄 PDF
Long baseline optical interferometric imaging with active phase stabilization
Astronomical observations allow us to better our understanding of the universe. As we observe smaller and more distance features, we run into the diffraction limit of our observation system. This limit is a function of the wavelength observed and the size of the primary aperture used. We can synthes…
Joshua J. Collier, Leuca Patmore, John S. Wallis, Elrina Hartman, Benjamin P. Dix-Matthews, David R. Gozzard · 📄 PDF
VQCSim: When Does Compile-Once Statevector Simulation Beat Generic Quantum Frameworks?
Hybrid quantum-classical machine learning workflows repeatedly evaluate many small parametrized circuits during training and model exploration. In this regime, framework dispatch and orchestration overhead often dominate runtime. Prior simulators accelerate execution but leave open the question of w…
Anton Firc, Martin Perešíni, Vojtěch Mrázek, Kamil Malinka, Vojtěch Staněk, Zbyněk Lička, Nouhaila Innan, Walid El Maoua… · 📄 PDF
From Tool Invocation to Source-Mechanism Exploration: Protected White-Box DSE for Open-Source EDA
Open-source EDA tools allow design-space exploration (DSE) to move beyond public knobs and into bounded source-level mechanisms inside staged optimizers. We present ReviewDSE, a protected white-box DSE framework that explores such mechanisms for a target design. ReviewDSE evaluates complete source c…
Zhiyu Zheng, Yiming Du, Ziyi Wang, Zhiang Wang · 📄 PDF
FPGA-Based Mini X-Ray Detector Front-End
Medical imaging systems require reliable front-end electronics that can acquire sensor data, process image information, identify errors, and communicate results to other parts of the system. In applications such as X-ray imaging, CT, PET, ultrasound, and other diagnostic imaging systems, the electro…
Kris Paetow, D. G. Perera · 📄 PDF
When and Why Naïve Diversification Works: A Simple Diagnostic Strategy
We explain the long-standing puzzle of naïve diversification with a simple, testable condition: equal weighting is minimum-variance optimal when the forecast-error covariance matrix has a uniform eigenstructure. This "Golden Criterion" drives a two-stage adaptive strategy that dynamically blends nai…
Han Feng, Difang Huang, Jue Wang, Zhengjun Zhang · 📄 PDF
Abnormal motions of optical vortex-antivortex-coupled wavepackets in the parabolic potential
The (quasi)particles or structured wavepackets in parabolic potential exhibit well-known harmonic oscillations, typically described by the Lissajous equations. However, such conventional harmonic laws rely on a fundamental assumption that the different constituent components of the (quasi)particles …
Haolin Lin, Junhui Jia, Chunhao Liang, Yanwen Hu, Boris A. Malomed, Yangjian Cai, Shenhe Fu · 📄 PDF
Leveraging Raman response in X-cut thin-film lithium tantalate for ultrabroadband combs and polychromatic visible light
X-cut thin-film lithium tantalate (TFLT) offers a unique combination of third nonlinearity, electro-optic effects, and a high optical damage threshold. However, its strong Raman response has historically hindered broadband Kerr comb generation. Here, we leverage this inherent Raman response by engin…
Xin Wang, Mingkun Xiao, Min Sun, Ronghong Gao, Yuqi Chen, Zhengshun Lei, Xun Zhang, Wenfeng Zhou, Jintian Lin, Yikai Su,… · 📄 PDF
Chiral lasing via broken parity-time symmetry in bound-state-in-the-continuum metasurfaces
We propose a concept for chiral lasing from planar metasurfaces that obviates the need for traditional out-of-plane symmetry breaking by exploiting spatial gain-loss modulation to break parity-time symmetry. We explain the underlying non-Hermitian physics of this design principle using a coupled-mod…
Matthew Parry, Daria A. Smirnova, Andrey A. Sukhorukov, Dragomir N. Neshev · 📄 PDF
A Nearable Soft Mat Based on Distributed Optical Fiber Sensing for Physiological Monitoring
Distributed optical fiber sensing (DOFS) combines the advantages of fiber optic sensors, including flexibility, small size, immunity to electromagnetic interference, and high metrological performance, with the capability to transform a single optical fiber into a continuous sensing element for spati…
Vincenzo Lavorgna, Martina Pulcinelli, Andrea Polimadei, Rosaria D Amato, Carlo Massaroni, Michele Arturo Caponero, Emil… · 📄 PDF
Geometry-Optimized Complex-Domain error-diffusion encoding for Fourier Single-Pixel Imaging
This work proposes a geometry-optimized complex-domain error-diffusion encoding method for Fourier single-pixel imaging. Instead of independently binarizing multiple grayscale phase-shifting patterns, the proposed method directly represents each complex-valued Fourier basis pattern using K (K >= 3) …
Chongwu Shao, Yue Cao, Wei Zhang, Xiaopeng-Jin, Yingran Shen, Shijian Li, Xu-Ri Yao · 📄 PDF
Tellurium Metasurface Beam Splitter with Pulse Laser-Controlled Anisotropy
Laser-programmable optical anisotropy offers a new route to developing reconfigurable metasurfaces without conventional nanofabrication processes. Here, we demonstrate a lithography-free approach based on spatial control of the crystallographic $c$ axis orientation in tellurium (Te) using pulse lase…
Takuto Hiraoka, Mizuho Matoba, Yuta Kobayashi, Arata Mitsuzuka, Masashi Kawaguchi, Haruyuki Sakurai, Kuniaki Konishi, Ma… · 📄 PDF
Mode-locking instability and multiple soliton formation in GaN polariton waveguide cavities
We study the emergence of multi-soliton regimes in 1D ridge polariton waveguides of two different lengths. We show that by varying the position of the gain, which in out-of-equilibrium polariton systems is provided by the pumping laser and its associated excitonic reservoir, it is possible to tune t…
O. Bahrova, V. Develay, H. Souissi, C. Brimont, L. Doyennette, B. Alloing, E. Cambril, S. Bouchoule, T. Ackemann, J. Zun… · 📄 PDF
Twist tunable resonances in photonic bilayer for second harmonic generation
Moiré structure emerging in photonic bilayers stacked with a twist enables the controllable frequency selective resonant response. Here, we employ twist tunable resonances to boost second harmonic generation (SHG) at a desired frequency in twisted photonic bilayers integrated with two-dimensional no…
Egor S. Vyatkin, Sergey A. Tarasenko · 📄 PDF
Generative AI in Higher Education Laboratory Learning: A Qualitative Case Study of Epistemic Scaffolding and Assessment Boundaries
Advanced physics laboratories require students to integrate disciplinary knowledge, experimental practice and scientific argumentation across complex observational and analytical tasks. The increasing availability of generative artificial intelligence (GenAI) adds complexity to this coordination, si…
Matteo Tuveri, Alessandro Riggio · 📄 PDF
Heterogeneous-Gradient Phase--Polarization Alignment and Maximal-Ratio Weight Allocation for Multi-Aperture Coherent FSO Reception
Multi-aperture coherent reception can improve freespace optical (FSO) links by converting spatial diversity into coherent combining gain. In turbulent links, the aperture branches are simultaneously affected by relative phase errors, polarization mismatch, and unequal signal-to-noise ratios (SNRs). …
Cheng Chen, Tong Luo, Jiayin Xue, Siyu Gong, Qun Zhang, Linsheng Fan, Qi Wu, Yanfu Yang · 📄 PDF
A diode nanocavity for fast, efficient and tunable emission of highly entangled photon pairs and Fourier-transform-limited single photons
Deterministic sources of entangled photon pairs and indistinguishable photons are expected to play a key role in photonic quantum technologies. Semiconductor quantum dots are promising candidates due to their on-demand emission and compatibility with nanophotonic structures. However, current impleme…
Ievgen Brytavskyi, Thomas Oberleitner, Christian Weidinger, Maximilian Aigner, Gabriel Undeutsch, Tobias Steindl, Johann… · 📄 PDF
NaBiF$_4$: Er$^{3+}$, Yb$^{3+}$ upconversion particle as a multi-functional bio-marker
Lanthanide-doped upconversion particles (UCPs) have revolutionized optical bioimaging platforms because of their excellent photostability, non-toxicity, and utilization of near-infrared excitation, which facilitates deep tissue penetration with negligible autofluorescence. However, it remains a chal…
Atanu Ghosh, Krishna Kumari Swain, Agniva Das, Mrutyunjaya Rath, Snigdhadev Chakraborty, Bipeen Kumar, Yamini Selvam, Si… · 📄 PDF
Drill-bit-inspired dynamic focal fields for augmented laser materials processing
Laser manufacturing has advanced through increasingly precise control of power, pulse duration, repetition rate and scan trajectory, yet the spatial intensity profile of the beam is still usually fixed during light-matter interaction. This constraint limits how energy can be delivered to matter, par…
Evangelos Skoulas, Pinku Yadav, Justin Hidjam, Aurelien Woher, Rainer Kling, Beat Neuenschwander, Alexander Rack, Xavier… · 📄 PDF
Axion Generation in a Three-Dimensional Optical Trap
The axion is a theoretical particle that could resolve multiple fundamental problems, most notably the strong Charge-conjugation-parity-symmetry (CP) problem in quantum chromodynamics and the nature of dark matter.To date, however, the axion has never been detected in any free-space experiment. In t…
Chunyu Zhang, Xinran Fang, Lichen Peng, Xuri Yao, Xiaoying Tang · 📄 PDF
The Dielectric Bowtie Effect: Classical Electromagnetic Edge Singularities in Subwavelength Cavities
Dielectric bowtie nanocavities can concentrate light into subwavelength regions without the ohmic losses of plasmonic metals. We show that this enhancement is the finite-geometry realization of a classical electromagnetic edge singularity. Unlike an isolated dielectric wedge, the scaling in a bowtie…
Valdemar Bille-Lauridsen, Jesper Mørk · 📄 PDF
Analytical Theory of Photon Tunneling and Near-Field Heat Transfer Between Dissimilar Materials
Near-field radiative heat transfer can exceed the blackbody limit through evanescent-mode coupling across nanoscale gaps. This enhancement underpins applications including thermophotovoltaic energy conversion, electroluminescent cooling, thermal rectification, and photon absorption in plasmon-assist…
Kartika N. Nimje, Mariano Pascale, Georgia T. Papadakis · 📄 PDF
Spacer-Mediated Gold Nanocube Arrays for Edge-Localized Excitonic Enhancement in Monolayer MoS2
Plasmonic nanostructures offer an effective route for enhancing light-matter interaction in atomically thin semiconductors, whose optical response is intrinsically limited by their sub-nanometer active thickness. Here, we numerically investigate excitonic enhancement in monolayer (ML) Molybdenum Dis…
Abdullah Efe Yildiz, Emre Ozan Polat · 📄 PDF
Phase synchronization dynamics of two mutually coupled InP lasers in a quantum entropy source
Quantum random number generators, at the core of digital trust infrastructures, rely on quantum entropy sources (QESs) to produce randomness from physical processes. The quantum origin certification of a QES requires a physical model compatible with the measured signal of the device. Here, we study …
Berta Martínez-Pàmias, Miquel Rudé, Cristina Masoller · 📄 PDF
Analytical Markov Chain for Spatiotemporal Flux Evolution of the Inner Filter Effect in Fluorescent Media
Characterizing emission and decay time spectra in multi-component fluorescent media is essential for identifying intrinsic material properties and optimizing detectors. However, wavelength evolution from the secondary inner filter effect (IFE) distorts these observable spectra. While Monte Carlo (MC…
Xuhui Yang, Guofu Cao · 📄 PDF
Direct writing of individual quantum dots
Quantum light sources capable of generating single photons are fundamental building blocks for photonic quantum technologies. In the ongoing search for an ideal quantum emitter, inorganic halide perovskite nanocrystals have emerged as a promising source of single photons. Their unique optical respon…
Weikun Zhu, Natalie Ngoh, Shelly Ben-David, Maxwell Conte, Teddy Hsieh, Sarah O. Spector, Tara Sverko, Patricia Jastrzeb… · 📄 PDF
Introducing entropy measures to PK/PD models in propofol anesthesia as a replacement of BIS
Depth of anesthesia is a complex but important vital state to analyze during a surgery or other procedure. One parameter to estimate this state is the bispectral index (BIS), a value ranging from 0 to 100 with a target of 40 to 60 for a stable state during surgery, which is based on the electroencep…
Alexander Edthofer, Christina Huber, Fabrizio Renzaglia, Andreas Körner · 📄 PDF
Quantum Arithmetic Circuits in Public-Key Cryptography
Quantum computing has advanced rapidly in recent decades, driven by developments across the technology stack, including quantum error-correcting codes and efficient quantum algorithms. Among these, quantum arithmetic circuits serve as fundamental building blocks for various promising algorithms. Des…
Siyi Wang, Kyungbae Jang, Hyunji Kim, Anik Basu Bhaumik, Anubhab Baksi, Hwajeong Seo, Anupam Chattopadhyay · 📄 PDF
Reliable Associative Lookup in Content-Addressable Memory
Content Addressable Memory (CAM) is an important memory paradigm, which performs fast search by comparing an input query against all stored entries in parallel, achieving $O(1)$ lookup complexity. CAM is typically built upon conventional memory technologies, such as SRAM and Non-Volatile Memory (NVM…
Fan Li, Yanan Guo, Xin Xin · 📄 PDF
From Tool Invocation to Source-Mechanism Exploration: Protected White-Box DSE for Open-Source EDA
Open-source EDA tools allow design-space exploration (DSE) to move beyond public knobs and into bounded source-level mechanisms inside staged optimizers. We present ReviewDSE, a protected white-box DSE framework that explores such mechanisms for a target design. ReviewDSE evaluates complete source c…
Zhiyu Zheng, Yiming Du, Ziyi Wang, Zhiang Wang · 📄 PDF
AtomFlow: An End-to-End FPGA-Based Control Architecture for Neutral Atom Quantum Computers
Neutral Atom Quantum Computing (NAQC) is an emerging modality for scalable quantum computation, valued for its long coherence times and the naturally identical atomic qubits. However, one of the main drawbacks is its slow execution rate, dominated by lengthy classical processing tasks, such as fluor…
Xiaorang Guo, Jonas Winklmann, Vengkeat Chea, Martin Schulz · 📄 PDF
Can LLMs Perform Deep Technical Comprehension of Computer Architecture Papers?
Can large language models perform deep technical comprehension of computer architecture papers -- not summarization, but structured critique that names the core mechanism, surfaces buried assumptions, and connects a contribution beyond its own scope? We study Gauntlet, an open-source pipeline that a…
Nishant Aggarwal, Ayushi Dubal, Sreeraj Kannakarankodi, Ian McDougall, Adarsh Mittal, Vishnu Ramadas, Noah Scott, Rangan… · 📄 PDF
DA-Nav: Direction-Aware City-Scale Vision-Language Navigation
City-scale outdoor navigation is currently hindered by the heavy reliance on dense maps or costly navigation supervision. In this work, we introduce a novel paradigm for leveraging directional instructions from commercial navigation tools (e.g., Google Maps). To bridge the gap between commercial ins…
Ye Yuan, Kehan Chen, Xinqiang Yu, Wentao Xu, Heng Wang, Libo Huang, Chuanguang Yang, Yan Huang, Jiawei He, Zhulin An · 📄 PDF
Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model
Recent foundation image and video generation models offer strong generalization and controllability, but their direct application to embodied scenarios is limited by requirements for multi-view consistency, geometric coherence, and robot embodiment constraints. Existing methods typically adapt found…
Xinghang Li, Jun Guo, Qiwei Li, Long Qian, Hang Lai, Yueze Wang, Hongyu Yan, Jiahang Cao, Xi Chen, Jingen Qu, Jiaxi Song… · 📄 PDF
Coordinated Incremental Trajectory Tracking of a Tailsitter Drone
This paper derives an analytical differential flatness transform for a tailsitter Unmanned Aerial Vehicle (UAV) under coordinated flight conditions using a simplified aerodynamic model. The proposed framework is formulated exclusively using rotation matrices, avoiding the ambiguities inherent to Eul…
Evangelos Ntouros, Ewoud J. J. Smeur · 📄 PDF
A Model for Mediating Multi-Modal Human Intent into Safe Maneuvers for UAVs
Direct human interaction with autonomous UAV systems can be enabled through modalities such as speech, gestures, and graphical interfaces. However, interpreting such inputs as directly executable commands introduces safety risks in dynamic environments. Operator requests may conflict with terrain co…
Sofia Nelson, Dalal Alrajeh, Pedro Antonio Alarcon Granadeno, Jane Cleland-Huang · 📄 PDF
Trajectory Planning and Certification for 3-DOF Robot Manipulators Using Real Quantifier Elimination Based on Comprehensive Gröbner Systems
We propose an algorithm and its implementation for trajectory planning and certification for 3-DOF robot manipulators. The method uses Real Quantifier Elimination (QE) based on Comprehensive Gröbner Systems (CGS), also known as the CGS-QE method. The main advantage of the proposed method is its effi…
Yu Nakai, Akira Terui, Masahiko Mikawa · 📄 PDF
Automated Synthesis of Facial Mechanisms for Conversational Animatronic Robots
Animatronic faces are a central component of socially interactive robots, enabling rich nonverbal communication through facial articulation. However, state-of-the-art animatronic faces are typically tailored systems: each new facial geometry requires extensive manual mechanical redesign, making larg…
Zongzheng Zhang, Zi Lin, Jiawen Yang, Ziqiao Peng, Junyan Lao, Lin Cheng, Huazhe Xu, Hang Zhao, Hao Zhao · 📄 PDF
Requirement-Driven Design of Whole-Body Social Tactile Sensing via Virtual Human-Robot Interaction
Tactile sensing for social-physical human-robot interaction (spHRI) is designed in a hardware-driven manner, where predefined sensor configurations constrain coverage, spatial resolution, and the range of recognizable gestures. We propose a requirement-driven framework that derives sensing requireme…
Dakarai Crowder, Ruohan Zhang, Alexis E. Block, Wenzhen Yuan · 📄 PDF
High-level spatial Dubins airplane-based reference smoothing with low-level geometric tracking for quadrotor control
A method for the control of quadrotors is presented. It is composed of a high-level reference smoothing step and a low-level reference tracking step. The high-level step leverages the Dubins airplane model for dimensionality reduction and reduced computational complexity, and exploits its structure …
Mogens Plessen · 📄 PDF
AutoPath: Learning Transferable Goal-Conditioned Stochastic Path Prior for Safe Navigation Without Human Demonstrations
Real-time navigation in cluttered and dynamic environments requires collision-free and dynamically feasible motion under limited perception. However, feasible navigation behaviors are inherently multimodal because multiple paths may exist around obstacles. In this paper, we formulate navigation as l…
Ziyang Zhang, Boyang Zhou, Zesong Yang, Haocheng Peng, Zeming Gai, Xiao Liang, Yujun Shen, Danping Zou, Ruizhen Hu, Huju… · 📄 PDF
A Compact Top-Loading Robot for Endovascular Interventions: Design, Control and Evaluation
Robot-assisted endovascular intervention can potentially reduce radiation exposure, improve surgeon ergonomics, enable telesurgery, support active assistance and autonomy, and enhance procedural precision. However, existing systems often suffer from limited procedural coverage because constrained pa…
Jonas Fischer, Lennart Karstensen, Franziska Mathis-Ullrich · 📄 PDF
MIRA: A Modular Open-Source Micro-UAV for Indoor Research
Indoor robotics research increasingly relies on micro-UAVs whose airframe, electronics, and control software are fully open to modification. Off-the-shelf platforms rarely expose the low-level access required for such modifications, while building a custom alternative typically requires substantial …
Lucas K. de Oliveira, Felipe A. G. Tommaselli, João Aires Marsicano, Marco S. Tayar, Pedro A. R. Saraiva, Ricardo V. God… · 📄 PDF
Casting Everything to Online API Services? A Survey of Integrating Localized Speech Recognition Models in Robotic Systems
Automatic speech recognition (ASR) has become a critical component of modern robotic systems because it is one of the most natural and intuitive ways for humans to interact with robots. A commonly used method is to directly use API services online. But is that all we can do? This article provides an…
Sheng Li, Jing Li, Felix Schijve, Jun Hu, Emilia Barakova · 📄 PDF
Active Noise Floor Estimation for Reliability-Optimal POMDPs: A Value-of-Noise-Information Approach
Finite Reliability Representations (FRR) certify when a cell-constant policy is sufficient for reliable decision-making in a partially observed system with a known physical noise floor. In practice, however, sensing and execution noise can be latent and context-dependent. This paper develops a certi…
Hyung-Jin Yoon · 📄 PDF
Robust bipedal locomotion on flowable slopes via foot-driven terrain manipulation
Bipedal robots are challenging to control because they operate close to instability, where small variations in foot-terrain contact can rapidly destabilize locomotion. On rigid terrain, bipedal robots mitigate this fragility by using well-established contact mechanics and control strategies. On flow…
Deniz Kerimoglu, Junnosuke Kamohara, Jiyeon Maeng, Ziwon Yoon, Seth Hutchinson, Ye Zhao, Daniel I. Goldman · 📄 PDF
Mixture of Frames Policy: Multi-Frame Action Denoising for Bimanual Mobile Manipulation
Robotic manipulation is inherently multi-frame: local actions may be simple in an end-effector frame, while transport, upright-object handling, and whole-body coordination are better represented in a base-aligned frame. However, modern diffusion-based visuomotor policies typically commit to a single…
Dian Wang, Jisang Park, Xiaomeng Xu, Han Zhang, Shuran Song, Jeannette Bohg · 📄 PDF
Backbone-Agnostic Perturbation-Induced Uncertainty Learning for End-to-End Real-World Image Dehazing
Real-world paired image dehazing remains challenging because haze degradation is spatially non-uniform, illumination-dependent, and physically ambiguous even when haze-free references are available. Existing end-to-end restoration networks usually formulate dehazing as a deterministic mapping from a…
Bingcai Wei · 📄 PDF
Motion4Motion: Motion Transfer Across Subjects at Inference
This work explores the motion transfer from one video to another, which is crucial in animation for diverse characters. Previously, video motion transfer has been largely explored between human and human-like characters, enabling a lot of applications in digital creation. However, these approaches e…
Ling-Hao Chen, Zixin Yin, Duomin Wang, Xianfang Zeng, Gang Yu · 📄 PDF
Event-RGB Adaptive Tracking for Nighttime Highway Perception
Intelligent Transportation Systems deployed on highways predominantly rely on conventional RGB cameras for traffic perception and vehicle tracking. However, highway environments present unique challenges: the absence of artificial lighting infrastructure, combined with high vehicle velocities, resul…
Haidong Wang, Hengxing Cai, Wanlei Li, Xiaogang Xiong, Renxin Zhong · 📄 PDF
Feature-Space Guided Diffusion for Realistic Ultrasound Image Synthesis
Conditional diffusion models can generate anatomically plausible medical ultrasound (US) images, but anatomical plausibility alone does not ensure realistic B-mode appearance. Most US pipelines adapt standard generative architectures and condition them on anatomical masks, or use guidance mechanisms…
Marina Domínguez, Nélida Mirabet-Herranz, Valery Naranjo · 📄 PDF
ABot-3DWorld 0: A Universal World Model to Explore Any 3D Space
We present ABot-3DWorld 0, a universal multimodal 3D world model that turns text, image, and video inputs into high-fidelity, explorable 3D worlds. At the heart of our framework is a unified Spatial Generative Primitive (SGP), a compact tuple of a high-quality panorama and a spatial point cloud that…
Mingchao Sun, Luyang Tang, Yu Liu, Xu Yan, Zhan Li, Yunwei Zhang, Fei Yu, Zengye Ge, Yumin Liu, Jiacheng Zhang, Yongchan… · 📄 PDF
Illuminant-Adaptive 3D Lookup Tables for Camera Color Correction
Color correction is a key component of camera image signal processing (ISP) pipelines, encompassing illuminant discounting and colorimetric mapping of device-dependent sensor responses to device-independent color spaces, such as CIE XYZ. Despite extensive research, accurate color correction remains …
Claudio Rota, Luca Cogo, Simone Bianco, Raimondo Schettini · 📄 PDF
SVI360: Spherical Video Interpolation
This paper addresses the problem of omnidirectional video interpolation, which plays an essential role in applications such as virtual reality and immersive video enhancement. Existing video interpolation methods are not well-suited for spherical videos, as they have difficulty handling severe disto…
Le-Kim Nguyen, Renato Martins, Pascal Vasseur, Cedric Demonceaux · 📄 PDF
GFR-SAM: Training-Free Referring Camouflaged Object Segmentation via Cross-Image Prompting
Referring Camouflaged Object Detection (Ref-COD) requires segmenting hidden targets guided by reference cues. While supervised methods are annotation-heavy and training-free approaches via sparse point-prompting are sensitive to localization errors, we propose GFR-SAM, a robust three-stage training-…
Yilong Yang, Jianxin Tian, Shengchuan Zhang, Liujuan Cao · 📄 PDF
Higher-Order Cell Tracking Transformer
Reconstructing lineages from live-imaging microscopy requires linking cell detections across time, including through cell divisions. A common approach is to construct a candidate graph and associate cell segmentations (nodes) across frames. However, these and other existing methods overlook two stru…
Jordão Bragantini, Ilan Theodoro, Loïc A. Royer · 📄 PDF
MicroCharNet: Less is More for License Plate Character Detection
License plate character detection is a crucial component of intelligent transportation systems, where high accuracy and computational efficiency are required for real-time deployment. Although recent deep learning-based methods have substantially improved detection performance, many high-accuracy mo…
Huy Che, Dinh-Duy Phan, Duc-Lung Vu · 📄 PDF
Cycle-World: Mitigating Error Accumulation in Long-term Video World Models via Reverse-Prediction Cycle Consistency
Autoregressive diffusion models have enabled high-quality video generation, yet their sequential nature inherently suffers from error accumulation. In long-horizon video synthesis, minor prediction deviations compound over time, inevitably leading to unconstrained generative drift, structural collap…
Zihan Su, Teng Hu, Jiangning Zhang, Ruiyan Wang, Ran Yi, Lizhuang Ma, Dacheng Tao · 📄 PDF
HASTE: A Platform for Rapid Post-Disaster Building Damage Assessment
When a large disaster strikes, responders need a map of which buildings are damaged within hours. The models that do well on public benchmarks assume matched before-and-after imagery and a training set drawn from similar past events, and neither is usually available for a new disaster in its first d…
Caleb Robinson, Anthony Ortiz, Simone Fobi Nsutezo, Cameron Birge, Meygha Machado, Marcelo Duarte, Joaquin Rivero Rodrig… · 📄 PDF
Beyond the Single Camera: Agentic Multi-View Reasoning in Sports Video Understanding
Recent Multimodal Large Language Models (MLLMs) achieve strong performance on single-view video understanding benchmarks. However, sports videos involve dense occlusion, rapid motion, and complex interactions that are difficult to resolve from a single viewpoint. In practice, sports events are recor…
Kerui Chen, Jinglu Wang, Xiaoyi Zhang, Yan Lu · 📄 PDF
Latent-Identity Tuning in Text-to-Image Personalization Models
Generating and editing a person's face demands high precision, as even minor modifications can significantly alter a subject's perceived identity. Current personalization and editing methods built on general-purpose text-to-image models, however, often lack the precision required for fine-grained fa…
Daniel Garibi, Ronen Kamenetsky, Hadar Averbuch-Elor, Daniel Cohen-Or, Or Patashnik · 📄 PDF
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation
In this paper, we propose SpectraReward, a training-free reward function that turns pretrained MLLMs into off-the-shelf reward models for image-generation reinforcement learning. Instead of asking the MLLM to judge a generated image or answer decomposed verification questions, SpectraReward measures…
Runhui Huang, Qihui Zhang, Zhe Liu, Yu Gao, Jie Wu, Hengshuang Zhao · 📄 PDF
Self-Healing Visual Recovery for Autonomous Ground Vehicles Using Camera-Only Visual Odometry
Low-cost unmanned ground vehicles are often used in indoor places like warehouses, inspection corridors, and farm rows, where painted floor lines guide the robot. Line following is useful because it only needs one camera and little computing power, but it can fail when the line is blocked or turns s…
Jakob Solberg Berntzen, Safia Fatima, Leon Moonen · 📄 PDF
$\mathtt{Q^2SAR}$: overcoming classical bottlenecks in drug discovery via quantum multiple kernel learning
Quantitative Structure-Activity Relationship ($\mathtt{QSAR}$) modeling is a foundational computational methodology in early-stage drug discovery, heavily relied upon for predicting compound toxicity, bioavailability, and therapeutic potential. However, classical methods often struggle to effectivel…
Mariano Caruso, Daniel Ruiz, Alejandro Giraldo, Guido Bellomo · 📄 PDF
CatRetriever: Contrastive Representation Learning for Slab-to-Bulk Retrieval in Generative Catalyst Discovery
Inverse design is an emerging data-driven paradigm for efficiently navigating vast chemical spaces to discover new materials with targeted properties, and in the context of heterogeneous catalysis, surface generative models have recently advanced this goal by directly generating catalyst surface-ads…
Jungho Oh, Woosung Kim, Dong Hyeon Mok, Jonggeol Na, Seoin Back · 📄 PDF
NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception
Differentiable simulators have advanced policy learning and model-based control, yet actuator dynamics remain an important source of sim-to-real error. This is particularly acute on low-cost platforms, where the linear current-to-torque relation $τ= K_tI$ becomes unreliable during commanded-target t…
Zhiyang Dou, John U. Onyemelukwe, Hangxing Zhang, Heng Zhang, Minghao Guo, Yunsheng Tian, Michal Piotr Lipiec, Joshua Ja… · 📄 PDF
HiFi-LLP: High-Fidelity, Low-Cost Latency Predictors with Confidence for Robust HW-NAS
With deep neural networks (DNNs) increasingly deployed on edge devices, hardware (HW)-aware optimization techniques--such as HW-aware compression and HW-aware neural architecture search (HW-NAS)--have become essential. These methods rely on real feedback from the target hardware to tailor DNN archit…
Shambhavi Balamuthu Sampath, Behzad Shomali, Nael Fasfous, Moritz Thoma, Judeson Anthony Fernando, Lukas Frickenstein, P… · 📄 PDF
When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems
As multi-agent, tool-using LLM systems are deployed, a common safety net is a runtime monitor that checks each message, tool call, or step on its own. We show this net has a fundamental hole. A distributed backdoor splits a harmful payload across agents, so every local check passes while the assembl…
Yibo Hu, Ren Wang · 📄 PDF
Paradoxes of Game Theoretic Equilibria and Price of Anarchy
For decades, static solution concepts (Nash, Correlated, and Coarse Correlated Equilibria) and the Price of Anarchy (PoA) have formed the bedrock of algorithmic game theory, with no-regret learning proving fast convergence to such game-theoretic equilibria. We show that reducing multi-agent learning…
Georgios Piliouras, Ian Gemp, Siqi Liu, Luke Marris · 📄 PDF
From Global to Factor-Wise Expert Composition in Discrete Diffusion Models
Discrete diffusion models offer a powerful framework for solving complex reasoning tasks, particularly through compositional generation, which combines multiple pre-trained experts to generalize beyond their individual training data. Recent theoretical corrections introduce time-dependent mixing wei…
Haozhe Huang, Yudong Xu, Abhijoy Mandal, Alán Aspuru-Guzik · 📄 PDF
From Expressivity to Sample Complexity: Narrow Teachers for Transformers via C-RASP
A theoretical understanding of Transformers is crucial to better understand the capacities and limitations of large language models (LLMs). There is much work analyzing the expressivity of attention-based models. By proposing handcrafted weights or using computational complexity arguments, a large a…
Michael Rizvi-Martel, Satwik Bhattamishra, Guillaume Rabusseau, Michael Hahn · 📄 PDF
An Exact Instrument for State Usage in Selective State-Space Models, and the Input-Driven Migration It Reveals
Selective state-space models such as Mamba route information through a bank of first-order modes whose input coupling is set by a learned selection mechanism. We give an exact instrument for measuring how a trained model uses these modes. Because the state matrix is diagonal, each channel's output d…
Raktim Bhattacharya · 📄 PDF
Relaxing Faithfulness with Intervention-Only Causal Discovery
Causal discovery algorithms learn a network that describes the causal dependencies among random variables. A common workflow involves first utilizing conditional independence properties on observational data to determine partially directed causal relationships, then applying interventions to orient …
Bijan Mazaheri, Jiaqi Zhang, Caroline Uhler · 📄 PDF
Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks
Quantum Neural Networks (QNNs) are a promising framework for quantum machine learning on near-term quantum devices, but their security risks remain insufficiently understood. Studies have shown that QNNs are vulnerable to backdoor attacks, yet existing quantum backdoors mostly rely on a fixed trigge…
Junrui Zhang, Zemin Chen, Lusi Li, Mohammad Ghasemigol, Daniel Takabi, Rui Ning · 📄 PDF
A Durability and Cross-Language Transfer Benchmark for a Validated Teaching-Feedback Classification Protocol
Institutions collect far more open-ended teaching-evaluation feedback than they read. A prior study introduced a validated protocol for classifying such comments by thematic category and sentiment, built from a documented annotation guide, an intra-annotator reliability measurement, stratified cross…
Esteban U. Vega Barajas · 📄 PDF
Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data
Compression is fundamental to intelligence. A model that can represent its training data as a short code has discovered regularities that enable generalization. Large neural networks may learn functions far simpler than their parameter counts suggest, but it is challenging to construct codes that re…
Shikai Qiu, Marc Finzi, Yujia Zheng, Kun Zhang, Andrew Gordon Wilson · 📄 PDF
From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence
Artificial general intelligence ultimately requires agents that can reason and act in the physical world. Action models, vision-language-action policies, and world models have advanced this goal, while World Action Models (WAMs) are particularly promising because they connect candidate interventions…
Yuanzhi Liang, Xufeng Zhan, Haibin Huang, Chi Zhang, Xuelong Li · 📄 PDF
Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction
Self-refinement often fails to strengthen few-shot inductive reasoning in large language models. Prompting a model to explicitly state its inferred rule does little on its own. What actually matters is a structurally enforced isolation between reasoning stages, so that information can only pass betw…
Huan Zhu · 📄 PDF
Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming
Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable. Red-teaming must therefore keep pace with evolving models and tools. Existing approaches mainly optimize attack success and preserve a…
Xutao Mao, Xiang Zheng, Cong Wang · 📄 PDF
VoxENES 2026: Benchmarking Generalization of Speech Spoofing Detectors Against LLM-Era TTS and Voice Conversion
Modern LLM-driven text-to-speech (TTS) and voice conversion (VC) systems produce synthetic speech that differs from the generators represented in many legacy spoofing benchmarks. This mismatch creates a temporal generalization gap that can overestimate detector robustness under real-world post-proce…
Aastha Sharma, Guangjing Wang · 📄 PDF
An Explainable Agentic System for Detection of Conversational Scams with Summary-Based Memory
Following the rapid progress of generative Artificial Intelligence, there is a growing threat posed by conversational scams. These scams often span over multiple weeks or months, gradually build trust and request for money or sensitive information. Existing scam-detection systems mainly focus on iso…
Ahmed Omar Salim Adnan, Yogananda Manjunath, Shivanjali Khare · 📄 PDF
Active Offline-to-Online Reinforcement Learning
Background: Offline reinforcement learning (RL) enables effective policies to be trained from large, previously collected datasets and subsequently improved through limited online interaction. This offline-to-online RL (O2O-RL) paradigm is particularly promising in nonstationary domains where intera…
Alper Kamil Bozkurt, Shangtong Zhang, Yuichi Motai · 📄 PDF
Time-Lag-Aware Deep Reinforcement Learning for Flexible Job-Shop Scheduling in PPVC Module Factories
Prefabricated prefinished volumetric construction moves most building work into module factories, whose production floor operates as a flexible job shop. A major complication is decisive: long post-operation time-lags caused by concrete curing, watertightness ponding tests, and paint drying, during …
Ziheng Zhang, Wei Zhang · 📄 PDF
Playful AI in Professional Email: A Field Experiment on Tone and Recipient Engagement
Large language models (LLMs) are rapidly reshaping workplace communication, yet whether AI-assisted writing changes how recipients actually behave, and through what channel, remains unknown. Here, in a randomized crossover field experiment, 121 employees across six companies sent work emails under t…
Ziv Ben-Zion, Teddy Lazebnik · 📄 PDF
Evaluating RE Practices for Explainability: Synthesizing Insights from Daimler Truck into an Explainable RE Framework Proposal
Explainability has emerged as a critical requirement for AI-based systems, particularly in safety-critical and regulated domains. Although prior research has proposed frameworks, patterns, and user-centered approaches to support explainability, there is limited empirical understanding of how existin…
Umm-e- Habiba, Lucas Mauser, Jonas Fritzsch, Justus Bogner, Stefan Wagner · 📄 PDF
StoryTeller: Training-Free Narrative Grounding for Long-Form Audio Description
Long-form audio description (AD) requires more than describing visible actions: it must preserve characters, events, relationships, and story context across scenes so that blind and low-vision (BLV) audiences can follow a film. Modern video-language models (VLMs) are effective on short clips, but th…
Seung Hyun Hahm, Minh T. Dinh, SouYoung Jin · 📄 PDF
Encoder-Side Neuron Identification and Amplification for Acoustic Perception in Large Audio-Language Models
Large audio-language models (LALMs) often underperform on fine-grained, non-semantic attributes of speech, such as a speaker's emotion, despite strong performance on speech content. Improving this without the cost of retraining calls for an effective inference-time intervention, yet most existing me…
Yu-Han Huang, Chih-Kai Yang, Ke-Han Lu, An-Yu Cheng, Hung-yi Lee · 📄 PDF
Introducing Human-Centeredness in AI-Assisted Lexicography
This paper proposes a human-centered artificial intelligence (HCAI) framework for AI-assisted lexicography. While generative AI offers significant opportunities to enhance lexicographic work, it also raises concerns regarding the future role of lexicographers and the preservation of linguistic and c…
Antonio San Martin, Catherine Trekker · 📄 PDF
MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents
We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents. The framework provides a stateful execution environment spanning 500+ tools across 16 application domains, supporting multi-image, multi-turn tasks where agents must ground progressively arri…
Kaixin Ma, Di Feng, Alexander Metz, Jiarui Lu, Eshan Verma, Afshin Dehghan · 📄 PDF
Transformer-Guided Swarm Intelligence for Frugal Neural Architecture Search
Neural Architecture Search (NAS) has automated the design of deep learning models but traditionally requires massive computational resources, often measured in thousands of GPU-days. In this paper, we propose a frugal and memetic NAS framework designed to democratize architecture design on consumer-…
Romain Amigon · 📄 PDF
LoRA-Based Cascaded Multimodal Fusion for Action Recognition in Medical Training Environments
This paper presents a cascaded Low-Rank Adaptation (LoRA)-based multimodal fusion framework for action and activity recognition in healthcare-oriented training environments. The proposed architecture combines parameter-efficient modality-specific adaptation with sequential fusion, enabling modalitie…
Divya Mereddy, Jeevan Beedareddy · 📄 PDF
Evidence-Backed Video Question Answering
Current Video Large Language Models (Video LLMs) excel in question answering (QA) but largely operate as black boxes, providing textual answers without verifiable visual grounding. Existing explainability efforts rely on textual rationales or sparse bounding boxes, which struggle to capture complex …
Shijie Wang, Honglu Zhou, Ziyang Wang, Ran Xu, Caiming Xiong, Silvio Savarese, Chen Sun, Juan Carlos Niebles · 📄 PDF
Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias
Existing studies of LLM-as-judge scoring bias work predominantly at the input-output level: they perturb inputs, measure score deltas, and propose prompt-level mitigations. We argue that the same biases admit a representation-level account in the judge's hidden state, complementary to the input-outp…
Zixiang Xu, Sixian Li, Huaxing Liu, Xiang Wang, Shuai Li, Zirui Song, Xiuying Chen · 📄 PDF
A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulation
Recent work in humanoid whole-body control has found success with a simple recipe: retarget human motion to robot kinematic references, then train policies via reinforcement learning (RL) to track them. But how does this recipe transfer to dexterous manipulation? The answer is not obvious, as manipu…
Yunhai Feng, Natalie Leung, Jiaxuan Wang, Lujie Yang, Haozhi Qi, Preston Culbertson · 📄 PDF
Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks
We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language models. While previous works on Transformer learning dynamics have so far been mostly tied to specific tasks, we study a generalized class of inductive tasks that unifies several synt…
Tiberiu Musat, Tiago Pimentel, Nicholas Zucchet, Thomas Hofmann · 📄 PDF
Metacognition in LLMs: Foundations, Progress, and Opportunities
Metacognition is a foundational component of intelligence critical to effective learning, problem solving, decision-making, communication, and more. In recent years, it has become increasingly recognized as a cornerstone of capable, transparent AI systems. Yet while LLMs have made significant progre…
Gabrielle Kaili-May Liu, Areeb Gani, Jacqueline Lu, Jordan Thomas, Mark Steyvers, Arman Cohan · 📄 PDF
Not All Family Firms Are Alike: How Founder-Led and Governance-Entrenched Family Control Shape the Trading Environment Around the Firm
Family-firm scholarship offers competing predictions about whether family control protects or threatens market integrity. We argue that the answer depends on how family involvement is exercised. Drawing on socioemotional wealth and agency-entrenchment perspectives, we examine 8,634 U.S. firm-years (…
Douglas Cumming, Esteban Hernandez, Shan Ji · 📄 PDF
Scaffold splits hide structural-frontier failures in ADMET models
Molecular property models are commonly evaluated by holding out Bemis--Murcko scaffolds, yet a scaffold identifier is only one notion of chemical unfamiliarity. We introduce a label-free structural-frontier split that reserves the sparsest and most physicochemically remote scaffold groups, and evalu…
Jiacheng Zheng, Chang Guo, Zixuan Wang, Xinyu Liu · 📄 PDF
Sandscapes: self-modifying energy landscapes with emergent branching and flips
Energy landscapes provide a common framework for describing learning, embryonic development, and collective dynamics. Although such landscapes may evolve over time, their dynamics are typically prescribed externally rather than generated by the system itself. Here we get inspiration from biology to …
Nacer Eddine Boukacem, Madhav Mani, Paul François · 📄 PDF
ARMOR-IMC: Adaptive Resource Mapping for Operational Robustness via Secure In-Memory Computing
The massive data-movement overhead in traditional architectures has led to the adoption of In-Memory Computing (IMC) for energy-efficient Deep Neural Network (DNN) processing. By leveraging emerging devices like Spin-Orbit Torque Magnetic Tunnel Junctions (SOT-MTJs), IMC bypasses the "memory wall" a…
Muhtasim Alam Chowdhury, Ramtin Zand, Soheil Salehi · 📄 PDF
MDQEC-QAS: Meta-Decoding for Quantum Error Correction with Hardware-Aware VQC Search and Confidence-Gated Recovery
We propose a unified meta-decoding framework for quantum error correction that learns syndrome-to-recovery mappings across multiple stabilizer codes and noise settings, without requiring separate decoders for each configuration. The benchmark includes FiveQubit, Steane, Planar3x3, and Planar5x5 code…
Prashant Kumar Choudhary, Nouhaila Innan, Muhammad Shafique, Rajeev Singh · 📄 PDF
Soft-Error Characterization and Hardening Trade-offs in Static PCHB Asynchronous Circuits
Pre-Charge Half Buffer (PCHB) is a promising asynchronous digital design paradigm for harsh-environment operation; however, its soft-error characteristics remain largely unexplored. This paper presents a systematic soft-error characterization and hardening trade-off analysis for static PCHB circuits…
Ramya Karri, Srija Rasoori, Ashiq A. Sakib · 📄 PDF
Edge Physical AI Deployment of Vision Transformers on Heterogeneous Edge GPU Targeting Autonomous Vehicles
Physical AI systems, such as autonomous vehicles and intelligent machines, require transformer-based perception models that satisfy stringent edge latency and energy constraints. However, heterogeneous edge-GPU deployment remains limited by underutilized hardware engines and accelerator-incompatible…
Ashiyana Abdul Majeed, Mahmoud Meribout, Neethu Joseph, Abel Kidane Haile, Mohammad Abdullah Al Faruque · 📄 PDF
IRONSmith: A Visual Dataflow Design Environment for AMD Ryzen AI NPUs
Machine learning inference increasingly relies on specialized hardware accelerators for throughput and power efficiency. Neural Processing Units (NPUs), such as the AMD Ryzen AI NPU, offer significant ML advantages over CPUs and GPUs, but programming them requires expertise in specialized frameworks…
Brock Sorenson, Samer Ali, Curt John Bansil, Aman Arora · 📄 PDF
A Comparative Review of Methods to Create a Composite Index for Sustainable and Inclusive Wellbeing
Societal goals need to shift from over-reliance on gross domestic product (GDP) to broader aspects of sustainable and inclusive wellbeing (SIW). However, defining SIW and eventually measuring it with a single number is problematic because it involves many subjective and objective contributors that c…
Ricardo da Silva Vieira, Mario Biggeri, Peter Benczur, Robert Costanza, Joseph Eastoe, Tuuli Hirvilammi, Ida Kubiszewski… · 📄 PDF
Sharing economy in the era of full automation: Evidence from autonomous vehicle on-demand mobility services
The digital age has facilitated the sharing of underutilized assets. This paper focuses on privately owned autonomous vehicles (AVs), a unique class of robots that can move independently and provide transportation services. When not in personal use, private AV owners can lease their vehicles to a pl…
Xiaoyan Wang, Kenan Zhang, Yaochen Ma · 📄 PDF
Directional AI Advice: Experimental Evidence from Healthcare
Generative AI is fast becoming the first place people turn for expert advice. The advice it provides can be directional rather than neutral, shaped in part by the choices of its designers and regulators. When clients consult AI before meeting an expert, they carry this directional advice into a rela…
Yuyu Chen, Hongbin Li, Lingsheng Meng, Xinyao Qiu, Qingxu Yang · 📄 PDF
Measuring Consumption with Credit Card Data: Benchmarking and Beyond
We introduce a novel monthly county-level consumption dataset constructed from spending data on over 350 million credit cards in the Federal Reserve's Y-14M reports, covering over 3,000 U.S. counties since 2014. We first show that the data closely approximate traditional consumption measures, explai…
Aditya Aladangady, Ricardo Duque Gabriel, Carlo Wix · 📄 PDF
Multiband topological group-velocity control from slow light to light stopping
We introduce next-nearest-neighbor (NNN) couplings into a Harper--Hofstadter photonic lattice to establish a long-range topological photonic platform for group-velocity engineering. We show that the NNN couplings not only open a previously closed band gap but also flatten the dispersion of the edge …
Junhao Yang, Jiarui Wang, Jingyu Liu, Shirong Lin, Xinyuan Qi · 📄 PDF
Nyquist-Sampled Time-Domain Adjoint FDTD for Memory-Efficient Broadband Nanophotonic Inverse Design
Adjoint optimization is a cornerstone of broadband nanophotonic inverse design, but conventional time-domain implementations face a severe memory bottleneck because they retain forward-field histories at every finite-difference time-domain (FDTD) time step. Here, we show that this full time-step sto…
Mingyu Park, Owen D. Miller, Haejun Chung · 📄 PDF
Nanosecond Pulsed-Laser Treatment Couples Chloride Removal with Oxide Transformation in Salt-Corroded Carbon Steel
Maintaining carbon steel in marine environments requires surface treatments capable of simultaneously removing corrosion products and chloride contaminants whilst modifying the residual oxide layer. In this study, salt-contaminated SS400 carbon steel was treated using a Q-switched pulsed fibre laser…
Youichi Ishikawa, Yoshitaka Okuyama, Daishi Fujita · 📄 PDF
Ion-Implanted Silicon Nanoregions Enable Ultra-Low-Loss Trimming of Cladded Photonic Integrated Circuits
Photonic integrated circuits (PICs) have emerged as a key platform for information processing, including optical communication and computing. As PIC complexity increases, fabrication-induced response deviations accumulate, making post-fabrication trimming critical for unlocking their full potential.…
Zhongyu Tang, Shabnam Taheriniya, Seongmin Jo, Xinyu Ma, Akhil Varri, Anna P. Ovvyan, Vincent Spreter, Liam McRae, Xians… · 📄 PDF
Anomalous Reflection of Caustic Spin-Wave Beams in a Magnonic Waveguide
Reflection of waves at interfaces is conventionally governed by Snell's law, which follows from conservation of momentum parallel to the interface. Here we show experimentally that caustic spin-wave beams in anisotropic media obey a fundamentally different reflection mechanism. Applying time-resolve…
Franz Vilsmeier, Christian Back · 📄 PDF
Inverse-designed meta processing units for multi-task near-field photonic computing
Integrated photonic neural networks require optical operators that are simultaneously compact, matrix-general and compatible with task-level reconfigurability. Here we introduce a meta processing unit (MPU), an inverse-designed near-field photonic device that implements local complex matrix transfor…
Chu Wu, Zeyu Cai, Songtao Yang, Ruoyu Shen, Yinan Zhao, Haiou Zhang, Wei Chu, Xing Lin · 📄 PDF
Joint Discrete-Continuous Flow Matching for Open-Vocabulary Inverse Design of Multilayer Optical Coatings
Amortized neural inverse design typically remains closed-world: component choices are fixed vocabulary tokens, coordinate grids are frozen at training time, and continuous variables are discretized into sequence tokens. Multilayer optical coatings are an industrially important instance, coupling mat…
Zhiyi Li, Yuheng Jin, Yidan Huang, Nan Chen, Hongyan Fu, Yikun Bu · 📄 PDF
Doubly resonant enhancement of second-harmonic generation with in-plane phase matching in plasmonic metasurfaces on an AlInP slab waveguide
Nonlinear metasurfaces have attracted significant interest by offering the possibility to circumvent conventional phase-matching requirements of bulk nonlinear crystals, opening the way to efficient frequency conversion over ultrashort propagation distances. Here, we experimentally demonstrate metas…
Timo Stolt, Huayu Bai, Seyed Ahmad Shahahmadi, Jani Oksanen, Andriy Shevchenko, Radoslaw Kolkowski · 📄 PDF
Optimal slit width for high-precision orbital angular momentum measurement using angular double-slit interferometry
We demonstrate an optimization of angular double-slit interferometry for accurate measurement of orbital angular momentum (OAM) of vortex beams. By scanning the dynamic double slits, the topological charge (TC) magnitude is directly determined from the oscillation frequency of the on-axis intensity.…
Yu Jian, Xin Wang, Jiyang Zhang, Tao Chen, Manpeng Chang, Chen Liu, Weimin Wang · 📄 PDF
Broadband silicon photonic phase shifters driven by gradient optical forces
While initially deployed for optical interconnects, silicon photonics is increasingly being explored as a hardware platform for programmable optical systems, including linear optical processors, neuromorphic photonic networks, quantum photonic circuits and multiplexed sensor arrays. Common to most e…
Guillermo Arregui, Sander Jæger Linde, Magnus Vejby Nielsen, Bingrui Lu, Nikolaj B. Hougs, Babak Vosoughi Lahijani, Søre… · 📄 PDF
Intracellular luminescence thermometry: A story of disagreement, trust, and hope
Intracellular luminescence thermometry has long promised to reveal how heat is generated, dissipated, and regulated inside living cells. Yet, despite substantial progress, the field remains shaped by disagreement over the magnitude and physical plausibility of reported intracellular temperature grad…
Araceli de Aquino Samper, Liyan Ming, Daniel Jaque, Riccardo Marin · 📄 PDF
Low-latency FPGA-based electronic control system for fast preparation of defect-free atom arrays
The scalability of neutral atom quantum computing demands integrated electronic control systems with low latency, modular architecture, and real-time feedback capability. Here, we present an FPGA-based electronic control system that eliminates the PC from the feedback loop, integrating photon counti…
Ya-Dong Hu, Dong-Qi Ma, Tian-Yang Zhang, Liang Chen, Yi-Chen Zhang, Xiao-Kang Zhong, Wen-Yi Zhu, Hong-Jie Fan, Qing-Xuan… · 📄 PDF
Asymmetric high-harmonic generation from subwavelength bianisotropic resonators
High-harmonic generation (HHG) enables attosecond light pulses and table-top sources of coherent extreme-ultraviolet and soft X-ray radiation. Although HHG has long been associated with gases and plasma, nanostructured solids are emerging as new alternative sources enabling both the enhancement and …
Albert Mathew, Piyush Jangid, Rebecca Aschwanden, Yves Koppeler, Thomas Zentgraf, Sergey Kruk · 📄 PDF
DrugGen 2: A disease-aware language model for enhancing drug discovery
Current computational approaches for drug design typically focus on generating molecules conditioned on specific targets or general molecular properties, often neglecting the influence of disease context on target behavior and therapeutic outcomes. To address this gap, we introduce DrugGen-2, a nove…
Ali Motahharynia, Mohammadreza Ghaffarzadeh-Esfahani, Mahsa Sheikholeslami, Navid Mazrouei, Matin Irajpour, Yousof Gheis… · 📄 PDF
A Theoretical Framework for Stochastic Activity Prediction in Tensor Accelerator Wallace-Tree Multipliers
Tensor accelerator multipliers burn dynamic power on every clock cycle, even when sparse operands require very little internal switching. No existing technique addresses this: zero-detection requires exactly-zero operands, structural power gating requires an idle multiplier, and offline weight selec…
Prashanthi Metku, Chandra Gandu · 📄 PDF
CRIMP: Compact & Reliable DNN Inference on In-Memory Processing via Crossbar-Aligned Compression and Non-ideality Adaptation
Crossbar-based In-Memory Processing (IMP) accelerators achieve high-speed, low-power computing for deep neural networks (DNNs), but face three obstacles. First, floating-point (FP) arithmetic is incompatible with crossbars, and existing quantization schemes still require FP processors for scaling fa…
Shuo Huai, Hao Kong, Xiangzhong Luo, Shiqing Li, Ravi Subramaniam, Christian Makaya, Qian Lin, Weichen Liu · 📄 PDF
Who Needs DRAM? We Have Fiber
The rising pressure on DRAM availability and contract pricing reflects generative AI's massive high-performance memory requirements. This pressure is heavily compounded by hyperscale data center expansion, which now consumes a significant portion of global DRAM output. In this work, we propose a new…
Hannah Atmer, Thiemo Voigt, Yuan Yao, Stefanos Kaxiras · 📄 PDF
Detecting Ladder Logic Bombs in IEC 61131-3 PLC Programs using ESBMC-PLC+: A Formal Verification Approach with Trigger Synthesis
A Ladder Logic Bomb (LLB) is malicious control logic in a Programmable Logic Controller (PLC) program that lies dormant until a trigger activates a payload to manipulate actuators, forge sensor readings, or deny operator control. We observe that real malicious logic hides inside function-block bodie…
Pierre Dantas, Lucas Cordeiro, Waldir Junior · 📄 PDF
FPGN: Redefining Ultra-Fast Programmable Gate-based Neural Acceleration with Differentiable LUTs
Achieving nanosecond-scale inference latency for deep neural networks (DNNs) has become a primary architectural concern for latency-critical applications. While Field-Programmable Gate Arrays (FPGAs) offer a promising substrate for low-latency inference, conventional FPGA accelerators remain arithme…
Jiawei Liang, Haotong Qin, Linfeng Du, Xingyu Liu, Shangkun Li, Hui Yu, Michele Magno, Xinyu Chen, Jiang Xu, Wei Zhang · 📄 PDF
ESBMC-Arduino: Closing the Deployment Gap for Formal Verification of Open-Hardware PLCs
OpenPLC, Arduino OPTA, CONTROLLINO, and Industrial Shields M-Duino bring IEC 61131-3 to low-cost microcontrollers used in real automation and industrial control system (ICS) security research. Existing open-source verifiers for IEC 61131-3, including ESBMC-PLC, prove safety over an abstract scan-cyc…
Pierre Dantas, Lucas Cordeiro, Waldir Junior · 📄 PDF
Input-Constrained Spatiotemporal Tubes for Safe Navigation of Unknown Euler-Lagrange Systems in Dynamic Environments
Safe navigation in dynamic environments is challenging when system dynamics are unknown and actuator inputs are limited. Existing methods either rely on accurate models, require online optimization, or do not explicitly account for input constraints. This paper presents a real-time control framework…
Siddhartha Upadhyay, Ratnangshu Das, Pushpak Jagtap · 📄 PDF
X-ACTA: eXtended Analytic Center Tension distribution Algorithm for fixed and mobile cable-driven-parallel-robot
Steering Cable-Driven Parallel Robots (CDPRs) beyond their Wrench-Feasible Workspace (WFW) augments their capabilities in challenging scenarios such as during aggressive maneuvers or following a cable failure. In this context, although the determination of cable tensions is a well-studied topic, onl…
Domenico Dona', Vincenzo Di Paola, Alberto Trevisani, Matteo Zoppi · 📄 PDF
TFP: Temporally Conditioned Memory-Fusion Policies for Visuomotor Learning
Vision--Language--Action (VLA) policies such as $π_{0.5}$ and OpenVLA perform well on many manipulation tasks, but they are often reactive: the next action is predicted from the current observation, instruction, and proprioceptive state. This assumption breaks down in stage-dependent manipulation, w…
Yushen Liang, Yue Peng, Baosheng Jin, Tianluo Zhang, Xinyu Zhang, Shuyi Zhou, Zhuoran Chen, Xinqi Liu, Shenji Wan · 📄 PDF
INTENT: An LSTM Framework for Vehicle Intention Prediction in Intersection Scenarios with Comprehensive Ablation Analysis
Vehicle intention prediction is a pivotal aspect in the agility and safety of autonomous vehicles in all driving scenarios; if genuine enhancement of autonomous vehicles are required, we need to make them adopt human interpretation of driver's intention especially in cases that require a lot of huma…
Logine M. Zaki, Catherine M. Elias · 📄 PDF
AnyDexRT: Calibration-Free Dexterous Hand Retargeting with Few-Shot Human Guidance
Teleoperation is a key interface for controlling dexterous robotic hands and collecting demonstrations for imitation learning. Its effectiveness largely depends on kinematic retargeting, which maps operator hand motions to feasible and intuitive robot hand motions. Existing methods often require han…
Chenxi Wang, Ying Feng, Hongjie Fang, Shangning Xia, Lixin Yang, Chuan Wen, Cewu Lu · 📄 PDF
SkillPlug: Unsupervised Skill Mining for Few-Shot Adaptation in Robotic Manipulation
Learning transferable visuomotor imitation policies that generalize across diverse manipulation tasks and adapt rapidly to new tasks from only a handful of demonstrations remains challenging. Most modern policies are trained end-to-end to map observations directly to low-level actions, offering litt…
Zi-han Ding, Ziwei Wang · 📄 PDF
FSD-VLN: Fast-Slow Dual-System Modeling for Aerial Long-Horizon Vision-Language Navigation
Vision-Language Navigation (VLN) enables UAV autonomous navigation in unknown environments by mapping language instructions to real-time visual inputs. Compared with GPS-dependent or pre-programmed navigation, VLN supports intuitive human-machine interaction and stronger environmental adaptability, …
Xueke Zhu, Qingyan Meng, Liutao Yu, Wei Zhang, Zhengyu Ma, Huihui Zhou, Yonghong Tian · 📄 PDF
Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition
Personality recognition has traditionally been constrained by theory-dependent formulations, where models are trained to fit predefined psychological taxonomies rather than uncovering shared underlying behavioral structure. This limits generalization, as personality itself is better understood as th…
Jing Jie Tan, Ban-Hoe Kwan, Danny Wee-Kiat Ng, Yan-Chai Hum, Shih-Yu Lo, Po-An Chen, Noriyuki Kawarazaki, Kosuke Takano,… · 📄 PDF
On Exploring Input Resolution Scaling For Anytime LiDAR Object Detection
Making tradeoffs between execution latency and result utility (i.e., anytime computing) for adapting to dynamic operational requirements has been shown to enhance the performance of cyber-physical systems. In this work, we focus on enabling anytime computing for deep neural networks (DNNs) that proc…
Ahmet Soyyigit, Shuochao Yao, Heechul Yun · 📄 PDF
Swapping Faces, Saving Features: A Dual-Purpose Pipeline for Pedestrian Privacy in ITS
Large-scale and diverse datasets are needed to train AI models to take real-time decisions for autonomous vehicles (AVs), an intelligent transportation system (ITS) application. Pedestrian intention and trajectory prediction are critical models used in AVs, requiring datasets involving diverse pedes…
Roba H. Farouk, Catherine M. Elias · 📄 PDF
Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents
Language-conditioned manipulation requires both precise contact-rich control and robust reasoning over language, scenes, and long horizons. End-to-end Vision-Language-Action (VLA) models provide strong local visuomotor skills, but they are trained on in-distribution task trajectories and often fail …
Yixian Zhang, Huanming Zhang, Feng Gao, Xiao Li, Zhihao Liu, Chunyang Zhu, Jiaxing Qiu, Yuchen Yan, Jiyuan Liu, Wenhao T… · 📄 PDF
Early to Share, Late to Save: Synchronisation-Driven Communication Gating in Bandwidth-Constrained Cooperative VLN
Most cooperative Vision-Language Navigation (VLN) methods assume unlimited communication, not considering real-world applications where bandwidth is restricted and information efficiency is critical. We introduce \textbf{bandwidth-constrained cooperative VLN} and propose \textbf{hindsight gating}: a…
Arav Gupta, Nivedan Yakolli, Avinash Gautam · 📄 PDF
FabriVLA: A Lightweight Vision-Language-Action Model for Precise Multi-Task Manipulation
We present FabriVLA, a lightweight Vision-Language-Action model for Precise Multi-Task Manipulation. FabriVLA combines an InternVL3.5 vision-language backbone with a flow-matching action head featuring gated self-attention across action tokens and shallow VLM layer fusion for enriched spatial contex…
Shiyuan Yang, Borong Zhang, Jizheng Zhang, Zhijia Tao, Junfei Guo, Donglai Ran, Xu Bian, Qingbiao Li · 📄 PDF
A New Human-Likeness and Comfort Index for Robot Movements Along Prescribed Paths
As human-robot interaction rapidly spreads in numerous fields, the subject of robot acceptance gains increasing importance. Visual similarity to the human body, as occurs for humanoids, is generally not enough to ensure acceptance in physical interaction, as acceptance directly links to comfort and …
Rosanna Coccaro, Enrico Ferrentino, Antonio Parziale, Angelo Marcelli, Pasquale Chiacchio · 📄 PDF
Learning Adaptive Solvers for Distributed Factor Graph Optimization on Matrix Lie Groups
Modern robotic perception increasingly involves large-scale geometric optimization problems distributed across multiple robots or sessions. However, existing distributed solvers often depend on brittle hand tuning and primarily target rigid body pose graphs. To address this, we present DeepCORD, a l…
Jaeho Shin, Maani Ghaffari, Yulun Tian · 📄 PDF
ContactMimic: Humanoid Object Interaction via Contact Control
Keypoint tracking alone is insufficient for object interaction tasks such as sitting on a chair, wiping a board, or pushing furniture, where the robot can reach the correct pose without making meaningful physical contact with the object. We present CONTACTMIMIC, a learning framework that tracks expl…
Xinyao Li, Xialin He, Runpei Dong, Saurabh Gupta · 📄 PDF
DexVerse: A Modular Benchmark for Multi-Task, Multi-Embodiment Dexterous Manipulation
Building general-purpose dexterous manipulation policies requires benchmarks that go beyond isolated tasks to systematically evaluate policies across diverse interaction modes, sensory conditions, and robot embodiments. However, existing benchmarks remain limited in task and data diversity, embodime…
Yunchao Yao, Zhuxiu Xu, Tianqi Zhang, Zixian Liu, Sikai Li, Zhenyu Wei, Feng Chen, Dihong Huang, Kechang Wan, Chenyang M… · 📄 PDF
VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Tokenization and Vector Database Retrieval
Open-vocabulary object detection and segmentation aim to recognize arbitrary objects beyond predefined categories. Although recent vision-language and reference-based approaches have significantly advanced this field, they often rely on text prompts, limited visual examples, or expensive feature mat…
ZhiXin Sun · 📄 PDF
Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning
Multimodal Large Language Models (MLLMs) often follow a fixed Think-then-Answer paradigm, which is inefficient in heterogeneous multitask settings because simple inputs may not require explicit reasoning while difficult ones can benefit substantially from it. Learning when to think is also unstable …
Yiyang Fang, Pei Fu, Jinjie Li, Jian Liang, Wenke Huang, Ruijie Luo, Shaojie Zhang, Jian Luan, Yi R. Fung, Mang Ye · 📄 PDF
Native Video-Action Pretraining for Generalizable Robot Control
The advent of video-action models offers a promising path for robot control. Nevertheless, we argue that repurposing video generative models designed for digital content creation is inherently inadequate for physical environments. To bridge this gap, we present LingBot-VA 2.0, a video-action foundat…
Qihang Zhang, Lin Li, Luyao Zhang, Shuai Yang, Yiming Luo, Shuaiting Li, Ruilin Wang, Junke Wang, Jiahao Shao, Gangwei X… · 📄 PDF
Do Transformations Reveal the Truth? Generative Residual Learning for Generalized AI-Generated Image Detection
The rapid advancement of generative AI has enabled the creation of highly realistic deepfake media, posing significant threats, including misinformation, digital identity theft, fraud, and manipulation of public opinion. AI-generated image (AIGI) detection is reliably challenging due to the diversit…
Kutub Uddin, Nusrat Tasnim, Awais Khan, Mohammad Umar Farooq, Khalid Malik · 📄 PDF
Multi-Resolution Feature Stem for Diabetic Retinopathy lesion segmentation
Diabetic Retinopathy (DR) is a leading cause of preventable blindness worldwide, requiring automated lesion segmentation using deep learning models for early detection and monitoring. However, DR lesions vary dramatically in size from tiny microaneurysms to large hemorrhages and exudates. This varia…
Indranil Dutta, Taehee Jeong · 📄 PDF
SAM-MT: Real-Time Interactive Multi-Target Video Segmentation
Modern Video Object Segmentation (VOS) involves tracking and segmenting user-specified targets. While recent approaches have achieved remarkable performance in single-target scenarios, extending them to multi-target settings typically involves replicating the single-target processing for each indivi…
Ruiqi Shen, Chang Liu, Henghui Ding · 📄 PDF
HumanForge: A Human-Centric Deepfake Video Benchmark with Multi-Agent Forgery Rationales
Rapid advancements in video diffusion models and temporal editing tools have enabled the generation of highly realistic human-centric videos, posing unprecedented challenges to digital content forensics. Existing benchmarks primarily focus on either face-swapping or global text-to-video synthesis, o…
Wenbo Xu, Zhimin Chen, Xiaojie Liang, Hengrui Liu, Wei Lu · 📄 PDF
WaspMOT: A Benchmark for Long-Term Multi-Object Tracking of Trichogramma Wasps
Multi-object tracking (MOT) has achieved strong performance on benchmarks dominated by short video sequences. However, such datasets do not adequately evaluate long-term identity preservation, where objects must be tracked consistently over extended durations. We introduce WaspMOT, a benchmark desig…
Tomasz Stanczyk, Yuan Gao, Hardik Agarwal, Seongroo Yoon, Tiantao Zhang, Vincent Calcagno, Francois Bremond · 📄 PDF
Enhancing In-context Panoramic Generation via Geometric-aware Pretraining
In this work, we present Canvas360, a two-stage framework for in-context panoramic generation that combines geometry-aware pretraining with downstream task-specific fine-tuning. To address the lack of large-scale, high-quality training data tailored to in-context panoramic tasks, we propose Canvas36…
Haoran Feng, Ruiyang Zhang, Longyi Zhang, Dizhe Zhang, Lu Qi · 📄 PDF
OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators
We propose OPSD-V, an on-policy self-distillation paradigm for post-training few-step autoregressive (AR) video diffusion models. Existing few-step AR video generators can produce long videos with low latency, but still suffer from error accumulation and weakened motion dynamics during long autoregr…
Hongyu Liu, Chun Wang, Feng Gao, Xuanhua He, Yue Ma, Ziyu Wan, Yong Zhang, Xiaoming Wei, Qifeng Chen · 📄 PDF
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
Scaling 3D Gaussian Splatting (3DGS) to large outdoor scenes is costly in both data acquisition and computation. Adopting panoramic images with equirectangular projection (ERP) can reduce capture effort via their full $360^{\circ}$ field of view, yet the resulting omnipresent visibility invalidates …
Weijian Chen, Weibo Yao, Yuhang Zhang, Xiaolin Tang, Guo Wang, Weijun Zhang, Xitong Gao, Yihao Chen, Hongde Qin, Lu Qi · 📄 PDF
LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models
Recovering high-quality video from sparse event streams is a challenging task. Regression methods often blur textures, while existing generative models struggle with long-term stability. We propose LongE2V, a novel approach that leverages pre-trained video diffusion priors to jointly handle event-ba…
Cheng-De Fan, Chun-Wei Tuan Mu, Chen-Wei Chang, Chin-Yang Lin, Kun-Ru Wu, Yu-Chee Tseng, Yu-Lun Liu · 📄 PDF
ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device
Monocular depth estimation has seen remarkable progress through foundation models achieving robust zero-shot generalization, yet their computational demands place them far beyond the reach of embedded and mobile platforms. Lightweight alternatives exist, but have been developed almost exclusively wi…
Fabio Tosi, Luca Bartolomei, Matteo Poggi, Stefano Mattoccia · 📄 PDF
Wat3R: Underwater 3D Geometry Learning without Annotations
Estimating 3D geometry in underwater environments presents unique challenges due to light attenuation, scattering, and the absence of large-scale, high-quality 3D annotations. Pioneering methods rely on massive dense annotations that are impractical in underwater settings. In this paper, we propose …
Jiangwei Ren, Xingyu Jiang, Zijie Song, Wei Xu, Hongkai Lin, Dingkang Liang, Xiang Bai · 📄 PDF
Federated Deep Learning for Privacy-Preserving Cardiovascular Disease Risk Prediction
Cardiovascular disease risk prediction models often rely on data from a single institution or centrally pooled datasets. Extending these models across institutions could be limited by privacy regulations and constraints on sharing patient-level data. Federated learning enables collaborative model de…
Hyunho Mo, Djura Smits, Mahlet A. Birhanu, Maarten J. G. Leening, Daniel Bos, Pim van der Harst, Esther E. Bron · 📄 PDF
Steering Neural Network Training through Interpretable Constraints Based on Partial Dependence
Over the last few years, there has been an increased interest in making machine learning models more interpretable. Although a great deal of effort goes into developing techniques for interpreting the interactions learned by a given model, fewer studies focus on assessing the quality of such explana…
Yann Claes, Pierre Geurts, Vân Anh Huynh-Thu · 📄 PDF
BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression
Large language models (LLMs) are increasingly constrained by memory capacity, weight bandwidth, and checkpoint storage during deployment. Existing low-bit compression methods mainly follow two directions. Scalar or group-wise quantization is simple and compatible with efficient low-precision kernels…
Yuantian Shao, Peisong Wang, Zhilei Liu, Chuangyi Li, Yuanteng Chen, Pengcheng Xie, Yiwu Yao, Zhihui Wei, Jian Cheng · 📄 PDF
Secure Decentralized Federated Learning via Gossip and Virtual Voting
Decentralized federated learning (DFL) removes the central server by letting nodes exchange model updates through peer-to-peer gossip, but existing gossip-based methods often lack provenance finality and resilience to Byzantine or lazy participants. Ledger-assisted federated learning (FL) improves a…
Amirhossein Taherpour, Xiaodong Wang · 📄 PDF
EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy
Graph Neural Networks (GNNs) have shown considerable success in learning from graph-structured data, but their use in privacy-sensitive areas remains difficult because graph structure can leak sensitive link information. To satisfy edge-level differential privacy, a common approach is to inject nois…
Wenxiu Ding, Muzhi Liu, Zheng Yan, Mingjun Wang, Yifan Zhao, Qiao Liu · 📄 PDF
Resample or Reroute? Budget-Aware Test-Time Model Selection for Large Language Models
Routing among large language models (LLMs) trades response quality against serving cost, motivated by the reported gap between deployed routers and a per-instance oracle. Recent analysis shows that test-time resampling can recover per-instance selection headroom that no single-commit router captures…
Teng-Ruei Chen · 📄 PDF
MPFlow: Learning Budgeted Max-Flow Optimization on the Lightning Network with Deep Graph Reinforcement Learning
We address liquidity placement in the Bitcoin Lightning Network (LN): given a fixed budget, which channels should a node open to maximize its routing capacity? We cast this as a budget-constrained combinatorial optimization problem on graphs, selecting $k$ edge additions that maximize $s$--$t$ max-f…
Harrison Rush, Vincent Davis, Simone Antonelli, Vikash Singh, Jesse Shrader, Emanuele Rossi · 📄 PDF
LTM: Large-scale Terrain Model for Wildfire-prone Landscapes
Accurate 3D terrain maps are essential for emergency response when assessing wildfire hazards. However, wildfire-prone regions often span vast areas where conventional reconstruction methods underperform. Airborne LiDAR systems provide high-resolution terrain data, but they are expensive and infrequ…
Xiao Fu, Yue Hu, Meida Chen, Peter Anthony Beerel, Barath Raghavan · 📄 PDF
Deep Learning for Joint Narrowband Interference Cancellation and Soft Demodulation in OFDM Systems
Narrowband interference (NBI) severely degrades orthogonal frequency-division multiplexing (OFDM) systems by corrupting subcarriers and rendering classical soft demodulation ineffective. Conventional compressed-sensing (CS) mitigation exhibits high sequential latency and leaves structured, non-Gauss…
Emmanouil Kavvousanos, Francky Catthoor, Vassilis Paliouras · 📄 PDF
Latent Memory Palace: Reasoning for Control as Autoregressive Variational Inference
Human decision-making is highly flexible -- some actions are taken immediately; others require longer deliberation. Language models have exhibited a similar capacity for adaptive "reasoning." However, transferring this capability to continuous control policies has been challenging, as directly reaso…
Chuning Zhu, Eva Xu, Jose Barreiros, Krishnan Srinivasan, Paarth Shah, Abhishek Gupta · 📄 PDF
Super Weights in LLMs and the Failure of Selective Training
Recent work identified Super Weights, individual parameters whose removal degrades model performance by orders of magnitude. We show that this degradation due to pruning Super Weights does not universally apply to all LLMs. Furthermore, if these parameters are so important, Super Weight-aware traini…
Shreyas Subramanian, Adewale Akinfaderin, Akarsha Sehwag · 📄 PDF
ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation
Generating realistic 3D human motions in real-time within interactive applications is key for animation, simulation, and humanoid robotics. While recent offline motion generation approaches offer precise control via text and kinematic constraints, they lack the inference speed required for interacti…
Kaifeng Zhao, Mathis Petrovich, Haotian Zhang, Tingwu Wang, Siyu Tang, Davis Rempe · 📄 PDF
MulTTiPop: A Multitrack Transcription Dataset for Pop Music
We present MulTTiPop, a dataset of pop music segments and their associated multitrack MIDI recordings for the evaluation of automatic music transcription models. MulTTiPop contains 572 segments of popular music totaling 3.5 hours of audio, and contains songs from diverse genres and decades from the …
Nathan Pruyne, Benjamin Stoler, William Chen, Chien-yu Huang, Shinji Watanabe, Chris Donahue · 📄 PDF
Score Accuracy Along the Forward Diffusion Does Not Certify Numerical Stability in Diffusion Sampling
Score matching controls average error under the forward marginals, but a discretized reverse-time sampler evaluates the learned score along its own trajectory. We show that small forward-marginal error does not guarantee numerical stability. We construct a single smooth score field with arbitrarily …
Yiwei Zhou · 📄 PDF
When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities
Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes a distinct concept. However, in vision-language models (VLMs), vanilla SAEs struggle to learn modality-consistent conce…
Weiduo Liao, Yunqiao Yang, Ying Wei · 📄 PDF
The complexities of patient-centred conversational artificial intelligence
Consumer-facing health chatbots powered by large language models (LLMs) are increasingly used for symptom assessment. However, chatbot development and evaluation often rely on cooperative, articulate, simulated patients. We analysed 2,053 real patient-chatbot conversations and found that communicati…
João Matos, Olivia Buege, Donny Cheung, Gary S. Collins, Paula Dhiman, Nan Li, Bingyu Mao, Benjamin W. Nelson, Michail O… · 📄 PDF
UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing
As available training data approaches its physical limit, gains from Scaling Laws have begun to diminish. Consequently, improving Large Language Models (LLMs) now depends less on data expansion and more on higher-quality data utilization. However, in the context of large-scale corpora, existing refi…
Xinlong Zhao, Dongsheng Liu, Hengyu Zhao, Zixuan Fu, Zheng Wang, Jie Cai, Jie Zhou, Qiang Ma, Xuanhe Zhou, Xu Han, Yudon… · 📄 PDF
Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning
As autonomous agents are increasingly deployed across diverse operational contexts, aligning their behavior with human intent demands reward functions that remain robust to such changes rather than overfitting to any single environment. Inverse reinforcement learning (IRL) provides a principled way …
Ali Larian, Qian Lin, Chang Zong Wu, Daniel S. Brown · 📄 PDF
Formal Mechanisms for Market Stability in Self-Interested Agent Societies: A Marketplace Simulation Study
Self-interested agents, left unconstrained, tend toward defection in repeated social dilemmas, causing cooperative gains from trade to collapse. This paper investigates what formal mechanisms, layered on top of unrestricted communication, are sufficient for a society of such agents to maintain marke…
Eugene Ng Yi Sheng, Bingquan Shen · 📄 PDF
WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search
Large language model (LLM)-based web search agents are transforming information seeking from simple factoid question answering into complex, deep-and-wide search and research-oriented tasks. A single ReAct-style agent is constrained by one long trajectory and limited context, making it difficult to …
Xiaoshuai Song, Liancheng Zhang, Kangzhi Zhao, Yutao Zhu, Zhongyuan Wang, Guanting Dong, Jinghan Yang, Han Li, Kun Gai, … · 📄 PDF
SolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decentralized Energy Markets
As agentic AI systems are increasingly applied to cyber-physical environments, their evaluation requires assessment of both task performance and trustworthiness. In decentralized energy markets, autonomous agents may improve market utility, but may also exploit invalid physical data, create artifici…
Shilin Ou, Yifan Xu, Luyao Zhang · 📄 PDF
A Practical Investigation of Training-free Relaxed Speculative Decoding
Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft tokens which are then verified in parallel by the LLM. Standard speculative decoding is lossless: its rejection and resampling steps exactly preserve the LLM's sampling distribution. Recen…
Guoxuan Xia, Luka Ribar, Paul Balanca · 📄 PDF
ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation
Repository-level code generation requires implementing target functions while accounting for complex cross-file dependencies and project-specific conventions. Existing retrieval methods predominantly rely on lexical, structural, or semantic similarity, often overlooking repository functions that imp…
QiHong Chen, Aaron Imani, Iftekhar Ahmed · 📄 PDF
Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act. As trajectories grow, task requirements, environment facts, prior attempts, diagnoses, and open subgoals can be buried in the context window or pushed bey…
Yifan Wu, Lizhu Zhang, Yuhang Zhou, Mingyi Wang, Bo Peng, Serena Li, Xiangjun Fan, Zhuokai Zhao · 📄 PDF
Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction
Recent progress in 3D human pose estimation has made markerless recovery of skeletal motion increasingly accurate and scalable. However, most pose estimators remain optimized for geometric keypoint accuracy, while many real-world applications in rehabilitation, sports science, ergonomics, and clinic…
Ayda Eghbalian, Kevin Desai · 📄 PDF
Validity of LLMs as data annotators: AMALIA on authority
A national language model offers a linguistic community its own instrument for measuring what its citizens say and value. Portugal's AMALIA, a publicly funded 9B-parameter model for European Portuguese, appears competitive on agreement alone: asked to code the moral foundation of authority, it agree…
Manuel Pita · 📄 PDF
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
Post-training quantization is widely used to deploy large language models in resource-constrained settings, yet its evaluation relies almost exclusively on accuracy and perplexity. We show that these metrics fail to capture behavioral changes induced by quantization. We introduce correctness agreeme…
Baha Rababah, Cuneyt Gurcan Akcora, Carson K. Leung · 📄 PDF
Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows
Large language model (LLM) applications increasingly use explicit workflows for tool use, retrieval, branching, checkpointing, and human approval. Existing workflow systems already address many execution concerns. This paper proposes a Lisp-inspired but language-independent conceptual model: symboli…
Emanuele Quinto, Carlo Andrea Rozzi, Francesco Zanitti · 📄 PDF
AUTOPILOT VQA: Benchmarking Vision-Language Models for Incident-Centric Dashcam Understanding
Recent advances in Vision-Language Models, Large Language Models, and Multimodal Large Language Models have improved autonomous driving tasks such as scene understanding, decision making, trajectory prediction, and visual question answering. However, evaluating whether these models can reliably reas…
Siddharth Damodharan, Radhika Gupta, Ali Alshami, Ryan Rabinowitz, Jugal Kalita · 📄 PDF
Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph
While UMAP is widely used for exploring high-dimensional data, typical workflows focus on its lower-dimensional embedding, largely overlooking the rich k-nearest-neighbor (kNN) graph that UMAP constructs internally. This graph encodes the data manifold in its original high-dimensional space, before …
Duen Horng Chau, Donghao Ren, Fred Hohman, Dominik Moritz · 📄 PDF
Using AI-based Learning Assistants in Higher Education: A Large-Scale Descriptive Analysis
In this study, we present a large-scale descriptive analysis of the use of an AI-based learning assistant (Syntea) in higher education. Based on objective log data from 77,543 students enrolled in distance studies, we examine usage patterns across gender, age group, study cluster, degree, and study …
Kristina Schaaff, Quintus Stierstorfer, Valerie Heckel · 📄 PDF
SLORR: Simple and Efficient In-Training Low-Rank Regularization
Low-rank factorization is widely used to compress neural networks, but modern models are often not naturally amenable to aggressive factorization without significant accuracy loss. Existing training-time low-rank regularizers can improve compressibility, but they often require SVDs of large weight m…
David González-Martínez, Shiwei Liu · 📄 PDF
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biological genomes. Current benchmarks still say little about whether AI systems can follow this inheritance structure. We present IdeaGene-Bench (IG-Be…
Yifan Zhou, Qihao Yang, Yan Li, Donggang Li, Xiru Hu, Hokin Deng, Ziyang Gong, Xuanyi Zhou, Huacan Wang, Xiangchao Yan, … · 📄 PDF
OpenCoF: Learning to Reason Through Video Generation
Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences. Recent video generation models offer a reasoning path distinct from previous Chain-of-Thought (CoT): reasoning can unfold through temporally connected frames, known…
Xinyan Chen, Ziyu Guo, Renrui Zhang, Dongzhi Jiang, Hongsheng Li · 📄 PDF
Cascading Effects of the COVID-19 Pandemic on Barangays in the Philippines
The COVID-19 pandemic disrupted socio-economic and healthcare systems in the Philippines, significantly affecting barangays. This study analyzes the cascading effects of the COVID-19 pandemic on key aspects of a barangay, namely mobility, accessibility of public services, economic and financial heal…
Naomi Ashley Amparo, John Frederick Muji, Paul James Montecillo, Jaymar Soriano, Vena Pearl Bongolan · 📄 PDF
Helping Hands, Healthier Infants: The Effect of Medicaid Doula Coverage Mandates on Birth Outcomes
Over the last decade a wave of U.S. states began reimbursing doula services through Medicaid, hoping to improve infant health and narrow stark racial gaps in birth outcomes. I evaluate these mandates using the staggered 2021-2024 rollout, a panel of 32.1 million births from CDC WONDER (2016-2024), a…
Farhad V. Farahani · 📄 PDF
The Impact of Publicly Funded Small Business Advisory Services: Firm Take-up and Performance in the United States
This paper studies the impact of geographic proximity to and utilization of publicly funded advisory services offered to US small businesses on firm take-up and performance. We leverage a novel administrative dataset from the Northern California Small Business Development Center (SBDC) Network cover…
Scott Kaplan, Ryan Raimondi · 📄 PDF
Inflation as an emergent phenomenon
We develop an agent-based model in which inflation emerges from decentralized price-setting and credit-financed production in an endogenous-money economy. Firms operate under working-capital constraints, form market-based price expectations through heterogeneous adaptive learning, and set prices via…
Alessio Emanuele Biondo, Mauro Gallegati · 📄 PDF
Quantum Dot Moiré from Crossed MoS2 Nanoribbons
Twisted atomically thin layers have attracted much attention for Moiré potential and correlated quantum phenomena. However, existing Moiré superlattices have largely been limited to extensive wavefunction without lateral confinement. Here we introduce a new platform where 1D nanoribbons of 2D MoS2 g…
Xinting Shuai, Hao Zhang, Wenjing Wu, Chongning Wu, Maryam Amiri, T. A. M. Ragib Shahriar, Dian Pan, Zhi Kai Ng, Tymofii… · 📄 PDF
Probing individual phonon-polaritonic nanoparticle-on-mirror cavities by infrared nanospectroscopy
Nanoparticle-on-mirror (NPoM) cavities enable extreme light confinement and strong light-matter interactions, but their realization with phonon-polariton materials in the mid-infrared spectral range remains largely unexplored. Here, we use nano-FTIR spectroscopy to study the near-field response of i…
Isabel Pascual Robledo, Iker Herrero León, Karol Kołataj, Guillermo P. Acuna, Javier Aizpurua, Philippe Roelli, Rainer H… · 📄 PDF
Ultra-high-speed chemiluminescence tomography of spinning-mode detonation waves
This work presents a chemiluminescence tomography campaign to reconstruct time-resolved, three-dimensional reacting structures in detonation waves propagating through ethylene-based mixtures at 1 atm. Images of chemiluminescence are recorded simultaneously by five cameras through a cylindrical sapph…
Amit K. Singh, Mateo Gomez, Kevin Y. Cho, Aaron W. Skiba, Samuel J. Grauer · 📄 PDF
Projected Energy Matching for Generative 3D Priors
Energy Matching has emerged as a powerful generative framework that combines flow model efficiency with the explicit likelihood of Energy-Based Models (EBMs) via a single, time-independent scalar potential. However, directly training this potential on high-dimensional 3D data remains computationally…
Daniel Barco, Michal Balcerak, Suprosanna Shit, Chinmay Prabhakar, Philipp Denzel, Bjoern Menze, Frank-Peter Schilling · 📄 PDF
A Sparse and Truncated State Vector Simulator for Peaked Circuits
In a class of quantum circuits known as peaked circuits, the goal is to predict the most probable bit string at the output of the circuit. Since these circuits are designed to have a sharp peak in their output distribution, in principle it should be possible to simulate them using a truncated state …
Diogo R. Ferreira · 📄 PDF
Identifying the MPC-Liquidity Gradient in High-Quality Data
We estimate the gradient of the Marginal Propensity to Consume (MPC) with respect to liquidity using a new estimator designed for administrative data with negligible measurement error in income. We derive a state-dependent consumption pass-through equation from the canonical buffer-stock model, and …
Mikael Carlsson, Marco D'Amico, Erik Öberg, Oskar N. Skans, Karl Walentin · 📄 PDF
Thermodynamic description of worldwide distribution of energy and carbon emission
Based on public data, we analyze the distributions of energy and carbon emission over world countries on a scale of the last 40-50 years using their presentation via Lorenz and Pareto curves. These curves in rescaled format remain remarkably stable on this time period being characterized by high val…
Klaus M. Frahm, Dima L. Shepelyansky · 📄 PDF
The Joneses Visit an Economics Lab
Existing literature offers persuasive evidence that individuals care about how their consumption compares to that of peers, and proposes a large variety of explanatory models. The present paper proposes a common framework for many of those models, and compares their ability to predict behavior in a …
Mikhail Freer, Daniel Friedman, Christian Ghiglino, Elke Weidenholzer · 📄 PDF
Answering Without Referring: How AI Search Rewrites the Web's Economic Bargain
Search engines have long allocated attention on the web by routing users from queries to websites. AI search changes this arrangement because information needs can be resolved inside the intermediary. Using URL-level Comscore U.S. desktop clickstream, we compare ChatGPT and Google information-seekin…
Qiaoni Shi, Kai Zhu, Kai Gu · 📄 PDF
Robustness to Model Uncertainties Drives More Rapid CO2 Emissions Reductions
Evaluating the economic impacts of climate policies is important for designing a response to climate change. One typical approach to assessing mitigation policy options uses integrated climate-economy models to analyze tradeoffs between the costs of reducing greenhouse gas emissions and the benefits…
Lisa Rennels, Frank Errickson, David Smith, Bryan Parthum, Klaus Keller, David Anthoff · 📄 PDF