11 Nov 2026

200 papers that day.

Picks that day

Pick of the dayBest new paper by our score

LowRAM: Low-Rank Keys and Amortised Values for Composable KV Cache Compression at Test-Time

In shortLowRAM compresses KV caches by predicting values from keys and low-rank key compression, achieving up to 5× faster decoding at 4× compression.

Published 4 Nov 2026

Trending60 upvotes on Hugging Face

SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes

In shortSplatAnything normalizes Gaussian spacing for feed-forward 3DGS, improving consistency across varied scenes and viewpoints.

Published 5 Nov 2026

Everything else

198 more papers from this day

Nov 9 Learning Heterogeneous Tactile Representation for General Dexterous Manipulation Bing Han, Yichuan Peng, Haoyu Dong + 16 more
TrendingOther ML
Nov 9 Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery Weida Wang, Benteng Chen, Yigeng Jiang + 87 more
AI for Science & Healthcare Reasoning & Agents
Nov 7 WorldFoundry: Towards Unified Infrastructure for World Intelligence Juanxi Tian, Jiadong Hou, Baiang Li + 13 more
Generative AI & Diffusion Computer Vision
Oct 30 Flide: Accelerating Decision Inference with Exact State Forking Bobo Li, Jiajia Song, Hao Fei + 2 more
LLMs & Language Models Reasoning & Agents
Nov 5 Toward the Era of Agentic Embodied Intelligence Chao Liang, Ke Chen, Fengxiaoxiao Li + 7 more
Other ML
Nov 9 Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning Haozhi Yuan, Handong Li, Yifan Zhang + 1 more
Multimodal AI Computer Vision Reasoning & Agents
Nov 5 PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers? Yue Zhang, Jilei Sun, Liqiang Jing + 2 more
RLHF & Alignment Reasoning & Agents
Nov 6 Longtail-SWE: High-Quality SWE Tasks for Underrepresented Languages Vladimir Dobrovolskii, Ibragim Badertdinov, Alexander Golubev
Reasoning & Agents Code & Software Engineering
Nov 5 ReproBridge: Building Reproducibility into ML Research Artifacts Yubo Wang, Rui Meng, Jaehyun Nam + 2 more
Reasoning & Agents
Nov 8 InfraRSI: Harnessing Recursive Self-Improvement for Training Infrastructure InfraRSI Team, Yuchuan Tian, Haocheng Mei + 8 more
Reasoning & Agents
Oct 30 Fast and Exact Relative-Position Attention via Structure-Aware Kernels Delyan Boychev, Ivo Petrov, Dimitar I. Dimitrov
LLMs & Language Models Efficient AI & Edge
Nov 5 FewStepRL: Fine-tuning Few-step Diffusion Models with Reinforcement Learning Haitao Lin, Minsi Ren, Yang Li + 4 more
LLMs & Language Models Generative AI & Diffusion
Nov 7 How Much Training-Inference Mismatch Can On-Policy Distillation Tolerate? Cong Yu, Ziting Wang, Songlin Jiang + 5 more
Efficient AI & Edge LLMs & Language Models
Nov 5 Steerable Multi-Objective Group-Relative Preference Optimization with Jointly Trained Low-Rank Adapters Constantinos Karouzos, Nikolaos Aletras
Efficient AI & Edge LLMs & Language Models ML Theory & Optimization
Nov 1 TRIO: Task Refinement with Individual Optimization for Retrieval-Augmented Generation Yingtao Ren, Xiao Luo, Yiwei Fu + 3 more
Reasoning & Agents LLMs & Language Models
Nov 5 SIRIS: Can LLMs Tell When Simulation Errors Matter in AI-Driven Systems Research Jinwoo Hwang, Sukmin Cho, Tao Zhang + 3 more
Reasoning & Agents
Nov 5 CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse Peter Belcak, Greg Heinrich, Saurav Muralidharan + 2 more
LLMs & Language Models Reasoning & Agents
Oct 30 Hierarchical Residuals: A Minimalist Decoupling of Residual Width from Compute Width Ziteng Wang, Jianqiao Lu, Xinyu Ma + 4 more
ML Theory & Optimization LLMs & Language Models
Nov 9 How Many Exposures Does a World Model Need? Learning Unseen Game Mechanics at Test Time Ku Onoda, Haruto Kawano, Shota Takashiro + 1 more
Computer Vision Reasoning & Agents
Nov 6 MotionGraphicsBench: Evaluating Motion Graphics Generation with Programmatic Verification Jiaju Ma, Ashvini Kumar Jindal, Chuhua Wang + 1 more
LLMs & Language Models Computer Vision Reasoning & Agents
Nov 4 IWIBench: Evaluating Gradient-Free Model Driven Intra-weight Injection Chris von Csefalvay, Pranav Doma, Achyuthan Unni Krishnan + 1 more
Other ML
Nov 3 FlyHash for LLM Agent Memory: An Empirical Validation and a New Application Mohan Bheemadolu, Chrisogonas O. Odhiambo
LLMs & Language Models Reasoning & Agents Efficient AI & Edge
Nov 8 SWAM: Scaling World Action Models with Cross-Modal Alignment Yu Zhou, Xinyuan Xia, Xuankun Yang + 8 more
Other ML
Oct 30 Auriga Technical Report: A Task-Agnostic Agent Harness for Zero-Shot Embodied Manipulation Chengcheng Wang, Yuheng Shi, Siyu Xu + 18 more
LLMs & Language Models Reasoning & Agents Multimodal AI
Nov 7 JoVox: Joint Hierarchical Flow Matching for Lightweight Voxel Generation Xiangjun Tang, Jianqi Chen, Peter Wonka
Generative AI & Diffusion Computer Vision
Nov 9 Training Vision Transformers to Focus: Emergence of Spatial Attention Head Specialization Yuji Nozawa, Yu-Chieh Lin, Youyang Ng
Computer Vision
Nov 5 PhysioWave-T: Token-Efficient Wavelet Foundation Models for Biosignals Yanlong Chen, Simone Benatti, Luca Benini + 2 more
Other ML
Nov 7 Spatial Harness: Grounding Spatial Reasoning in Executable World States with Physics Engines Chentao Cao, Zhanke Zhou, Sangni Duan + 2 more
Multimodal AI LLMs & Language Models RLHF & Alignment
Nov 6 Coding or Cheating? An Investigation of Frontier Coding LLMs Yuntao Gui
LLMs & Language Models Reasoning & Agents
Nov 8 Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimization Zhengyu Hu, Zheyuan Xiao, Yike Wang + 18 more
LLMs & Language Models Reasoning & Agents
Nov 5 e-means: outperforming k-means (in one-tenth the epochs) Swann Bessa, Pierre-Emmanuel Mazaré, Gergely Szilvasy + 4 more
ML Theory & Optimization Efficient AI & Edge
Nov 5 RidgeFill: Training-Free Late-Layer Cache Fill for Faster Prefill Dylan Johnston, Robert P. Smith
LLMs & Language Models
Nov 5 SkinMind: Equipping Agentic RAG with Human-Inspired Graph Probing for Reliable Dermatology AI Jing Hao, Weinan Zhou, Zhihong Lu + 11 more
Reasoning & Agents LLMs & Language Models Multimodal AI
Nov 6 InstantHMR : Real-Time Human Mesh Recovery on Your Phone Mohamed Adjel, Kahina Chalabi, Vincent Bonnet
Efficient AI & Edge
Nov 1 Stochastic Deep Supervision for Gallery-Consistent Early-Exit Face Recognition Guray Ozgur, Tahar Chettaoui, Eduarda Caldeira + 2 more
Computer Vision
Nov 5 All Quiet on the Neural Front: Language Models Do Not Report Injected Pain States Emilio Ferrara
LLMs & Language Models
Oct 27 AutoVend: Benchmarking LLM Agents on Long-Horizon Autonomous Vending Operations Qiming Shi, Yikun Li, Beidi Luan + 7 more
LLMs & Language Models RLHF & Alignment Reasoning & Agents
Nov 1 ODE Policy: Robot Learning via Action Dynamics, Not Actions Jindou Jia, Jingliang Li, Kuangji Zuo + 9 more
Other ML
Nov 5 Knowing When to Teach: Learning from Teachable Prefixes in Multilingual Reasoning Distillation Jaewon Cho, Minseo Yoon, Jinyoung Park + 4 more
Reasoning & Agents RLHF & Alignment
Oct 27 LCM-Promo: An LLM-Based Uplift Model for Promotion Allocation Nesta Midavaine, Floris Fok, Paulo Mendes + 4 more
LLMs & Language Models
Nov 2 Human-Centred, Risk-Constrained Evaluation of Financial Document Recognition: Evidence, Critical Errors, and Selective Automation Subodh Lonkar
AI Safety & Privacy
Nov 8 FraudBench: A Legal Evaluation of AI Deception Kevin Wei, Sumaya Nur Adan, Stephan Llerena + 17 more
LLMs & Language Models
Nov 8 EmoHarness: Boosting Multimodal Emotion Understanding with Meta-Harness Evolving Fenghai Li, Bingxuan Li, Jiawen Zhang + 4 more
LLMs & Language Models Computer Vision Audio, Speech & Music
Nov 8 Click3R: Interactive Stereo 3D Reconstruction with Sparse Correspondence Clicks Hao Gu, Jin Yao, Zezhou Cheng
Computer Vision
Nov 6 Energy-Tweedie: Score meets Score, Energy meets Energy Andrej Leban
Other ML
Nov 6 Horizon-Scalable Q-Learning Haoran Xu, Pragya Srivastava, Xinjie Liu + 2 more
AI Safety & Privacy
Nov 6 onóna: Twin Embeddings with Tied Unembeddings Cheng Luo, Xinnan Dai, Zhongzhu Zhou + 4 more
LLMs & Language Models Efficient AI & Edge
Nov 5 Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching Chuangtao Ma, Sriom Chakrabarti, Arijit Khan + 1 more
LLMs & Language Models Reasoning & Agents
Nov 8 Creative Priming: Decoupling Process from Product to Escape the Creative Paradox Alon Albalak, Sebastian Gabriel, David B. D'Ambrosio + 2 more
LLMs & Language Models
Nov 9 World In-Context Learning for Agentic Robot Manipulation Heng Fang, Zehui Guo, Yuehan Zhang + 3 more
Top pickLLMs & Language Models Computer Vision
Nov 9 Beyond Modality Preference: Controlling Multimodal Arbitration under Modality Conflict in MLLMs Zhaoying Pan, Shenyu Lu, Jun Hui Wong + 2 more
LLMs & Language Models Computer Vision Multimodal AI
Nov 9 Where Does Alignment Emerge and What Does It Mean? A Closer Look at the Platonic Representation Hypothesis Julia Herbst, Simon Roschmann, Quentin Bouniot + 1 more
LLMs & Language Models RLHF & Alignment Multimodal AI
Nov 9 Mitigating Agentic Deception via Evaluation-Side Partially Observable Games Hanxiao Li, Shutong Liu, Yongjia Ma + 11 more
LLMs & Language Models Reasoning & Agents
Nov 9 Anchor Behavior, Not Parameters: Rehearsal-Free Continual Learning with a Single Shared Prompt Duy-Cuong Bui, Trung-Anh Dang, Vincent Nguyen + 2 more
Efficient AI & Edge LLMs & Language Models Computer Vision
Nov 9 PORT: Preference Optimization via Robust Token-Level Reweighting Ding Zhu, Xiukun Wei, Tian Xie + 3 more
LLMs & Language Models RLHF & Alignment Reasoning & Agents
Nov 9 Learning inexact alternating minimization for convex problems with quadratic coupling Paul Häusner, Jevgenija Rudzusika, Jens Sjölund + 1 more
LLMs & Language Models ML Theory & Optimization
Nov 9 WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning Sang-Hoon Lee, Ha-Yeong Choi
Top pickAudio, Speech & Music RLHF & Alignment
Nov 9 MoSTE: Mixture of Spatio-Temporal Experts for Deepfake Detection in Videos Charbel Yahchouchi, Nabyl Quignon, Noemi Roggero + 2 more
AI Safety & Privacy Efficient AI & Edge
Nov 9 A Geometric Invariant of Attention Predicts Head Specialization from Weights Alone Miguel P. Bento
LLMs & Language Models AI Safety & Privacy
Nov 9 Zero-Search Reinforcement Learning for Slay the Spire 2 with Failure-Driven Restarts Xiangqin Chen, Zhengxuan Xie
LLMs & Language Models Reasoning & Agents
Nov 9 Weight-Space Programming for Medical Imaging: Do We Still Need Training Data? Maximilian Lindholz, Richard Ruppel, Annette Milnik + 11 more
LLMs & Language Models AI for Science & Healthcare Computer Vision
Nov 9 HyPLM Technical Report Haowei Lin, Cai Zhou, Xiangxin Zhou
LLMs & Language Models Reasoning & Agents Efficient AI & Edge
Nov 9 HyInv Technical Report Haowei Lin, Cai Zhou, Xiangxin Zhou
LLMs & Language Models Reasoning & Agents
Nov 9 MUTE: Multi-Level Alignment Uncoupling Against Talking-Head Exploitation for Voice Protection Donghyun Kim, Jin Hong, Seungmin Kim + 3 more
Computer Vision Audio, Speech & Music RLHF & Alignment
Nov 9 AnyBreak: Towards Jailbreaking Any T2I Model for Any Concept Qi Lu, Zehui Guo, Yucheng Zhao + 3 more
Generative AI & Diffusion Computer Vision RLHF & Alignment
Nov 9 3R-Adapter: Retrieval, Rewiring, and Refinement for Efficient Adaptation of 3D Reconstruction Model Zixiang Ai, Zhenyu Cui, Xu Zou + 1 more
Computer Vision Efficient AI & Edge LLMs & Language Models
Nov 9 LO-World: Unified BEV Latent Modeling for Joint 4D Occupancy and LiDAR Forecasting Zhimin Liao, Ping Wei, Kai Mao + 1 more
Generative AI & Diffusion Computer Vision
Nov 9 Spectral Unlearning: Transformer Structure-Preserving Updates for Language Models Sung Il Choi, Junhao Cai, Dohun Kim + 1 more
LLMs & Language Models ML Theory & Optimization AI Safety & Privacy
Nov 9 Answer or Defer? Testing VLMs' Stated Confidence on Brain MRI Amir Sabbaghziarani, Parsa Ghazvinian, Sepehr Salem + 1 more
Multimodal AI LLMs & Language Models Reasoning & Agents
Nov 9 When to Trust Adaptation: Contextual Fusion for Transferable Vision-Language Prompting Zhenyuan Chen, Wenshuo Tao, Zhuo Huang + 3 more
Multimodal AI Computer Vision
Nov 9 Guiding Data Allocation for Robust Subpopulation Generalization Zhaoying Pan, Yipei Wang, Shenyu Lu + 1 more
Other ML
Nov 9 A four-step validation protocol for radiomic survival analysis in small cohorts: a body composition case study Mariela Talavera-Muñoz, Cecilia Diana-Albelda, Miguel Antonio Sampedro-Nuñez + 3 more
ML Theory & Optimization
Nov 9 What Breaks Scribble-Supervised Segmentation? An Audit-Informed Benchmark for Scribble Annotation Robustness Minheng Wu, Di Wen, Ruiping Liu + 4 more
Computer Vision
Nov 9 When Does Sliced Inference Pay Off? Resolution, Tiling and Dense Fusion for Small Object Detection Stefan Becker, Jens Bayer, David Münch + 1 more
Computer Vision
Nov 9 MARS: Multiscale Appearance-Residual Streams for Video Forgery Detection Ahmed Y. Radwan, Shaina Raza
AI Safety & Privacy
Nov 9 Perturb, Aggregate then Reconstruct: Consensus Aggregation and Fourier-Attended Multi-Decoders for Reconstruction-based Multi-View Anomaly Detection Yongho Son, Junyeong Yun, Je Hyeong Hong
AI Safety & Privacy
Nov 9 Patching Up Circuit Learning via Parameter Sharing Charles Bricout, Gennaro Gala, Viacheslav Borovitskiy + 1 more
Generative AI & Diffusion
Nov 9 dNaViT: Discrete Codes are General-Purpose Visual Representations Xiaotong Li, Zhengrong Yue, Xu Huang + 9 more
LLMs & Language Models Computer Vision Generative AI & Diffusion
Nov 9 More Than Just Style: Benchmarking Personality Influence in Large Language Models Yuhao Liu, Mengyu Wang, Xiao Chen + 1 more
LLMs & Language Models
Nov 9 AutoVLA-D: Learn a Trajectory-Geometric Condition from Reasoning for Autonomous Driving VLA Yuguang Yang, Zhewen Tan, Canyu Chen + 9 more
Other ML
Nov 9 CADMA: Capacity-Aware Coverage Decomposition for Generative Model Assessment Debin Meng, Zheng Gao, Ziquan Liu + 3 more
Generative AI & Diffusion
Nov 9 GeoMind: A Benchmark for Spatial Understanding in Robotic Manipulation Jinghe Wang, Xinrui Cao, Duo Wu + 5 more
Reasoning & Agents
Nov 9 One-Shot Federated Graph Learning via High-Fidelity Proxies and Transferability-Guided Collaboration Jia Jiang, Zihan Tan, Wenke Huang + 2 more
Efficient AI & Edge
Nov 9 How a Model's Architecture and Performance Influences Explainability: A Study of Grad-CAM and CRAFT in CNN-Based Image Classification Kilian Göller, Haadia Amjad, Steffen Seitz + 2 more
Computer Vision AI Safety & Privacy
Nov 9 AscendMOEA: An Ascend NPU-Accelerated Platform for Tensorized Multi-Objective Evolutionary Algorithms Qianlong Dang, Zhiyang Zhang, Baosheng Li + 2 more
Other ML
Nov 9 FocusBranch: Combinatorial Branch-and-Bound for $\ell_0$ Neural Network Robustness Verification Renwei Deng, Yang He, Linyi Li + 1 more
Other ML
Nov 9 UltraVoxelGS: Voxel-First Feed-Forward Gaussian Splatting for 3D Ultrasound Reconstruction Yue Wang, Haoxin Chen, Xiaoqing Guo
Other ML
Nov 9 Can LLM Agents Organize Their Own Memory? Zichuan Fu, Junjia Qi, Wenlin Zhang + 5 more
Reasoning & Agents
Nov 9 LBSNet: Lightweight Brain State Modeling via Learnable Spectral Prototypes for EEG-Based Fatigue Detection Kun Jia, Zhenyu Cao, Hanlin Yu + 5 more
Efficient AI & Edge
Nov 9 Adaptive Entropy-Sparing for Efficient Reasoning Cong Jiang, Xiaofeng Zhang, Tom Ko + 1 more
Reasoning & Agents
Nov 9 SpinSCI: Mask-Conditioned Spatial-Temporal Spin Transformer for Video Snapshot Compressive Imaging Seungki Hong, Zhishuai Zhang, Taekwang Jang
Other ML
Nov 9 Breaking the $\sqrt{d}$ Communication Barrier in Federated Sampling with Adaptive Hamiltonian Monte Carlo Jiajun Liang, Linxuan Wang, Guang Lin + 1 more
ML Theory & Optimization
Nov 9 Adaptive Quantization Preserves Fast Rates for TD Learning over Rate-Limited Channels Sreejeet Maity, Aritra Mitra
Efficient AI & Edge Reasoning & Agents
Nov 8 HiVe-Mem: Interleaving Horizontal Memory Expansion and Vertical Evidence Composition for Multimodal Agents Haozhen Zhang, Bohan Liu, Jianzhu Bao + 5 more
Reasoning & Agents Efficient AI & Edge Multimodal AI
Nov 9 Vendi Anomaly Scores for Efficient and Accurate Anomaly Detection Amey Pasarkar, Adji Bousso Dieng
AI Safety & Privacy Efficient AI & Edge
Nov 9 Shortcuts and Boundaries: Verifiable RL Misalignment and Contextual Safety Learning Xinjie Shen
RLHF & Alignment Reasoning & Agents AI Safety & Privacy
Nov 9 WorkflowArena: Benchmarking Executable Workflow Orchestration in LLM-Based Multi-Agent Systems Zheng Jiang, Fang Niu, Bo Peng + 10 more
LLMs & Language Models Reasoning & Agents Code & Software Engineering
Nov 9 What kills $v$-prediction? A Patch-wise PCA Perspective on Pixel-Space Flow Matching Tianze Luo, Haofeng Huang, Yuan Yao
Generative AI & Diffusion Efficient AI & Edge
Nov 9 What the Loss Curve Misses: FP4 Pretraining Slows the Acquisition of Rare Facts Chang Lu, Mengjiao Zhang
LLMs & Language Models Efficient AI & Edge
Nov 9 2D Gum-Net: Unsupervised Dense Elastic Image Registration via Symmetric Correlation and Spectral Pooling Aarya Bhave, Anushka Ajay Bhave
RLHF & Alignment AI for Science & Healthcare
Nov 9 Agentic-OPD: Recovering Forgotten Agent Capabilities via On-Policy Distillation for Agentic Tasks Tingcheng Bian, Kangye Gong, Jinchang Luo + 6 more
LLMs & Language Models Reasoning & Agents
Nov 9 Complementarity-Driven Dual-Teacher Hierarchical Alignment for Zero-Shot EEG-to-Image Retrieval Lukun Wu, Jie Li, Ziqi Ren + 3 more
LLMs & Language Models Computer Vision
Nov 9 Large Language Models as a Universal Searcher for Open-World Automated Machine Learning Yuxuan Hu, Jihao Liu, Weikang Shi + 6 more
LLMs & Language Models Reasoning & Agents
Nov 9 LogCDM: Interpretable Log Anomaly Detection via Behavioral Graph Drift and Adaptive Signal Fusion Suryansh Talukdar, Taha Sarwat, Jin Soung Yoo
AI Safety & Privacy LLMs & Language Models
Nov 9 Inference Validation for Regulated AI: Building a Decision Pipeline on NVIDIA AIPerf Dev Akre, Roman Bobalo, Manoj Dobbali
LLMs & Language Models Efficient AI & Edge
Nov 9 Safe Reinforcement Learning for Multi-Turn Clinical Agents: When Dense Rewards Beat Outcome Rewards Brendan P. Murphy, Agustina Saenz
LLMs & Language Models Reasoning & Agents ML Theory & Optimization
Nov 9 OptiCover: A Scalable and Multi-Surface Framework for Cold-Start Visual Optimization under Semantic Constraints Guillaume Guy, Mihajlo Grbovic, Joe Mills + 5 more
Multimodal AI LLMs & Language Models Computer Vision
Nov 9 TrialDesignBench: Benchmarking Language Models for Phase-I Trial Design Against Clinical Knowledge Yihan Hank Tang, Peng Yang, Jiayi Xin + 5 more
LLMs & Language Models Reasoning & Agents
Nov 9 Beyond Sunny Skies: Using Large Language Models to Predict Urban Traffic in Adverse Weather Zhu Xiao, Kuan Feng, Tong Li + 4 more
LLMs & Language Models Reasoning & Agents
Nov 9 How Far Does Second-Order Linear Response Predict Quantization Mismatch? Pre-Registered Measurements on Five Language Models Dezhen Lu, Zixiang Ni
Efficient AI & Edge LLMs & Language Models
Nov 9 Double Blind Evals: Resolving the Dual Confidentiality Dilemma in AI Safety Auditing Andrew Trask, Sol Messing, Vai Pahwa + 27 more
LLMs & Language Models AI Safety & Privacy
Nov 9 Direct Conditioning of Audio Diffusion Transformers on fMRI Reveals Cortical Contributions to Sound Reconstruction Matteo Ciferri, Tonio Weidler, Matteo Ferrante + 2 more
Generative AI & Diffusion Computer Vision Audio, Speech & Music
Nov 9 Evaluating Cross-Signal Coherence in Mammography Vision-Language Models Rebeca Nam, Chase M. Fensore, Christian A. Fauria-Robinson + 2 more
Multimodal AI LLMs & Language Models Reasoning & Agents
Nov 9 GHiML: VLM-Guided Hierarchical Multi-Label Learning with Applications to Benthic Imagery Isaac Xu, Devi Ayyagari, Martin Gillis + 3 more
Multimodal AI Computer Vision
Nov 9 WanderBench: Can World Models Explore Dynamic Worlds from Video? Yuhang Chen, Jiheng Li, Jiale Wang + 2 more
Computer Vision Reasoning & Agents
Nov 9 SciMARS: Multi-Agent Recursive Self-Improvement for Closed-Loop Scientific Discovery Weimin Wu, Han Liu
Reasoning & Agents AI for Science & Healthcare
Nov 9 EditJudge-Bench: Auditing VLM Image-Edit Judges with Synthetic Ground Truth Jens Parslov, Marco Schouten, Dim P. Papadopoulos
Multimodal AI LLMs & Language Models Generative AI & Diffusion
Nov 9 Can the Confidence and Decisions of System 1 Models Be Trusted? An Explainability and Perturbation Audit of Jev-Style Decision Models Julien Delaunay
LLMs & Language Models AI Safety & Privacy Efficient AI & Edge
Nov 9 Phrase-Level Speculative Decoding on a Frozen Target Madhusudhana Naidu
Efficient AI & Edge LLMs & Language Models
Nov 9 To SIMD or Not to SIMD: Comparing RVV vs. CGRA SoCs for Non-Linear Functions in AI Sameer Deshmukh, Naoya Mizuki, Takumi Honda
Efficient AI & Edge LLMs & Language Models
Nov 9 Optimal Rates for Adaptive Private $k$-PCA Johanna Düngler, Amartya Sanyal
ML Theory & Optimization AI Safety & Privacy
Nov 9 Unprompted coordination through shared memory in LLM agents: a locked two-implementation replication and extension Pekka Abrahamsson, Muhammad Waseem, Esa Karjalainen + 5 more
LLMs & Language Models Reasoning & Agents Code & Software Engineering
Nov 8 PhysOPSD: Code as Privilege for Physically Plausible Video Generation Harold Haodong Chen, Rui Peng, Lingteng Qiu + 3 more
Generative AI & Diffusion LLMs & Language Models Computer Vision
Nov 9 AutoBuddy: Evaluating Proactive, Always-On Agents on Task Discovery and Execution in a Simulated Workplace Shiqi Chen, Daniel Madrigal Diaz, Wei-Ning Chen + 7 more
LLMs & Language Models Reasoning & Agents
Nov 9 Clinical predictions using artificial intelligence in neurosurgery and its subspecialties: a systematic review and meta-analysis Prajwal Ghimire, Aswin Chari, Jonathan Shapey + 1 more
AI for Science & Healthcare AI Safety & Privacy
Nov 9 AudioCodex: Streaming Autoencoders for Live Audio Marco Pasini, Javier Nistal, Cyran Aouameur + 2 more
Audio, Speech & Music RLHF & Alignment Efficient AI & Edge
Nov 9 TRIAD: Multimodal Retrieval across Abstraction, Constraints, and State Xiangyang Wu, Chen Ju, Xu Chen + 4 more
Computer Vision Multimodal AI
Nov 9 DForkTree: Accelerating Speculative Decoding with Fork-Aware Block Diffusion Draft Trees Zhicheng Zheng, Cheng Zhang, Chenkai Tang
Efficient AI & Edge LLMs & Language Models
Nov 9 TMT: Adapting CLIP to Infrared Imagery via Text-Derived Modality Knowledge Transfer Ruofan Wang, Puzuo Wang, Xin Chen + 3 more
Multimodal AI LLMs & Language Models Computer Vision
Nov 9 Rethinking Radar 3D Perception: Representation Learning from Raw Spectra Miao Zhang, Mohamed Abdelsamad, Bin Yang + 5 more
LLMs & Language Models Computer Vision
Nov 9 AMSchem: Automated Schematic Visualization of AMS Circuits via Verifiable Agentic Generation Yichen Shi, Zhiyuan Wang, Jianing Cui + 7 more
LLMs & Language Models RLHF & Alignment Reasoning & Agents
Nov 9 Tensor Network Kernel Machines for Nonlinear System Identification Kim Batselier
ML Theory & Optimization Efficient AI & Edge
Nov 9 Mitigating SM-Level Load Imbalance in 3D Gaussian Splatting on GPUs Junha Ryu, Hoi-Jun Yoo
ML Theory & Optimization Efficient AI & Edge
Nov 9 A Modular Perspective for Modeling MARL Systems Tiziano Maisonhaute, Jean-Christophe Soulié, Fabien Michel
RLHF & Alignment Reasoning & Agents
Nov 9 MNN-Pocket-0.3B Technical Report MNN Team
LLMs & Language Models Reasoning & Agents Efficient AI & Edge
Nov 9 HumanSightBench: A Benchmark for Human Visual Perception in MLLMs Zixin Su, Yangguang Lin, Zegang Peng + 10 more
LLMs & Language Models Computer Vision Reasoning & Agents
Nov 9 Physics-Informed Sinusoidal Representation Networks for Damage Identification in Ultrasonic Guided Wave Structural Health Monitoring Lukas Jilke, Caspar Wasle, Norbert Hosters + 3 more
AI Safety & Privacy Efficient AI & Edge
Nov 9 Depth as a Candidate Source: Portfolio Allocation for Recurrent Test-Time Scaling in Large Language Models Chaoyuan Hao, Wentao Yue, Yanyan Wu + 6 more
LLMs & Language Models RLHF & Alignment Reasoning & Agents
Nov 9 Representational Alignment between Deep Neural Networks and Human Brain in Speech Processing under Audiovisual Noise Cheng Luo, Jian Zhu, Zhoujian Sun + 4 more
Audio, Speech & Music RLHF & Alignment
Nov 9 VLA-MOPD: On-Policy Distillation for Multi-Task VLA Policy Consolidation Yongxuan Lv, Zhen Fang, Lichen Man + 10 more
Generative AI & Diffusion Multimodal AI
Nov 9 Learning Evidence-Grounded Reasoning for Context-Aware Time Series Forecasting Xingpeng Gao, Mingyue Cheng, Daoyu Wang + 2 more
Reasoning & Agents LLMs & Language Models
Nov 9 Agent4Crypto: A Dual-Reflective and Market-Feedback-Aligned LLM-Based Multi-Agent System for Cryptocurrency Trading Guangyan Gan, Jiahao Li, Jiashun Wang + 1 more
Reasoning & Agents LLMs & Language Models RLHF & Alignment
Nov 9 Prune, Don't Merge: Expert Compression of Mixture-of-Experts LLMs on Multilingual Production Tasks Tomas Rasymas, Povilas Kvedaras
Efficient AI & Edge LLMs & Language Models
Nov 9 A Cost That Practice Accuracy Hides: Worked Solutions in Self-Generated Training Data and the Compositional Use of New Rules Jiantong Xu
LLMs & Language Models Reasoning & Agents
Nov 9 PARIS: A multi-agent LLM framework for end-to-end, PRISMA-guided systematic literature reviews with pre-synthesis corpus quality assessment Christophe Cruz, Hussam Ghanem, Samir Jabbar + 2 more
LLMs & Language Models Reasoning & Agents
Nov 9 Learning to Act with World Models by Valuing What Comes Next Chenghao Gao, Zhi Zhang, Dian Jin + 2 more
RLHF & Alignment Reasoning & Agents
Nov 9 Harnessing Vision-Language Models for Federated Unsupervised Visual Recognition Jian Liang, Kuangpu Guo, Ran He + 1 more
Multimodal AI LLMs & Language Models Computer Vision
Nov 9 NearFormer: Linear-Size Sparse Attention via Randomized Near Neighbors Ali Parviz, Alex Cloninger, Gal Mishne
Efficient AI & Edge AI Safety & Privacy
Nov 9 Same Physics, Different Gradients: A State-of-the-Art Report on Differentiable Physics Simulation Lei Shu, Zizhou Huang, Yunuo Chen + 15 more
AI for Science & Healthcare ML Theory & Optimization
Nov 9 The balance between feature learning and collapse in dynamical systems-based generative models Julian Brandon, Bruno Loureiro, N Alex Cayco-Gajic + 1 more
Generative AI & Diffusion ML Theory & Optimization AI Safety & Privacy
Nov 9 DisasterVL: Evidence-Based Visual Reasoning Dataset and Model for Disaster Scene Understanding Ali Diba, Aisha Al-Mohannadi, Yin Yang + 2 more
Computer Vision Multimodal AI
Nov 9 Good Views Are Not Enough: Global Counterexamples for Gaussian-Regularized JEPAs Anran Xu
LLMs & Language Models RLHF & Alignment
Nov 9 Toward Sustainable Agentic AI: Carbon Tradeoffs Across Iterative Self-Refinement and Tool-Augmented Coding Boris Ruf, Adrien de Mailly Nesle, Marcin Detyniecki
Reasoning & Agents LLMs & Language Models
Nov 9 Lost in Rounding: bf16 Recurrent State Makes Hybrid Reasoning Models Think Longer Yuchuan Weng, Xin Chen, Chi Liu
Reasoning & Agents AI Safety & Privacy
Nov 9 CARE-PO: Controllable Tool-Call Efficiency for LLM Agents Xiaoyang Ye, Xiao Yao, Hairui Zhu + 6 more
Reasoning & Agents LLMs & Language Models ML Theory & Optimization
Nov 9 System Optimizations for Cost-Efficient Agent Harnesses Jongseok Park, Jiaxiang Yu, Eric Zhou + 6 more
LLMs & Language Models Reasoning & Agents
Nov 9 SCALE: Small-Model-First Concept Abstraction with LLM-Guided Experience Internalization Hong Su
Reasoning & Agents LLMs & Language Models
Nov 9 OGDA: Ontology-Grounded Data Agents for Reliable Analysis over Heterogeneous Data Lakes Boyi Zhang, Hong Ting Tsang, Yisen Gao + 6 more
LLMs & Language Models Reasoning & Agents
Nov 9 SkillDuet: Co-Evolving Models and Skills through Response Feedback Xingguang Ji, Ziqiang Dong, Yubo Zhang + 3 more
LLMs & Language Models RLHF & Alignment
Nov 9 SPARK: Simple Post-training for Adapting pRetrained Knowledge to Robot Control Taekyung Kim, Jeongeun Park, Byeongho Heo + 3 more
LLMs & Language Models Computer Vision
Nov 9 From Fluent Text to Ontology-Compatible Definitions: A Quality-Control Agentic Workflow Kun Feng, Chenchen Chu, Yan Liu + 6 more
LLMs & Language Models Reasoning & Agents
Nov 9 CRAFT-AI: Capability and Requirement Alignment for Flexible Manufacturing through Agentic AI Kiavash Fathi, Hans Wernher van de Venn
RLHF & Alignment Reasoning & Agents
Nov 9 Compass 1: Towards Open-World and Persistent Embodied Navigation from Monocular RGB Videos Hai Zhang, Siqi Liang, Yanjun Guo + 17 more
Generative AI & Diffusion Computer Vision Multimodal AI
Nov 9 Correct First, Fast Second: What a Local 7B Code Model Can and Cannot Do for GPU Kernel Optimization Jui-Chien Tsou, Po-Yi Wu
LLMs & Language Models RLHF & Alignment Reasoning & Agents
Nov 9 MIRIX-2.0: Multi-Agent Memory System Wei-Chieh Huang, Weizhi Zhang, Jiayan Nan + 2 more
LLMs & Language Models Reasoning & Agents
Nov 9 Translating KV Caches Between Hybrid-Attention Language Models: MLA Latents, Linear-Attention States and Sparse-Attention Indexers Povilas Kvedaras, Tomas Rasymas
Efficient AI & Edge LLMs & Language Models
Nov 9 BARS: Beat-Adaptive Rap Synthesis via Flow Matching Taemin Cho, Hector Martel, Enyan Koh
Generative AI & Diffusion LLMs & Language Models Audio, Speech & Music
Nov 9 COMPASS: Composable Policy-Amortized Structured Search for LLM-Based Optimization Modeling Nguyen Le Minh Hoang, Van Duc Cuong, Bui Trong Duc + 1 more
LLMs & Language Models RLHF & Alignment
Nov 9 BECON: Belief-Conditioned Constrained Multi-Objective Reinforcement Learning under Drifting Preferences and Budgets Bui Trong Duc, Huynh Thi Thanh Binh
Reasoning & Agents ML Theory & Optimization AI Safety & Privacy
Nov 9 Evaluating AI Agents for Industrial-Level Chip Floorplanning: A Framework and Empirical Study Nova-Silicon Team
RLHF & Alignment Reasoning & Agents
Nov 9 Four-Step Text-Bearing Image Generation via Distillation with Local Response Regularization and Teacher-Guided Training Kairui Wen, Sheng Ye, Yong-Jin Liu
Generative AI & Diffusion Computer Vision
Nov 9 SMO: Compiling Natural Language Skills into Graphs of Reusable State-Move-Outcome Bricks Chao Chen, Jiashuo Zhang, Yunhang Shen + 2 more
LLMs & Language Models Reasoning & Agents
Nov 9 Leveraging Complementary Event Frame and Voxel Representations for RGB-Guided Multimodal Pre-training Wentao Wu, Xiao Wang, Yi Wang + 3 more
LLMs & Language Models Generative AI & Diffusion Computer Vision
Nov 9 DPGS-SLAM: Diffusion-Prior and Provenance-Aware Monocular Gaussian Splatting SLAM for Dynamic Visual Sensing Yifan Luo, Takafumi Matsumaru, Vibekananda Dutta + 1 more
Computer Vision Generative AI & Diffusion
Nov 9 SAFE-Hair: Scalp-Anchored Fields for Exportable Single-View Hair Reconstruction Yucheng Wang, Zedong Wang, Yuetong Wu + 2 more
Generative AI & Diffusion Computer Vision
Nov 9 Single Image Super-Resolution via Semantic Prompt and Cross-Modal Training on Content Area Xiao Tan
Computer Vision Multimodal AI
Nov 9 TIRAD: Text-guided Image Residual Learning for Generalist Anomaly Detection Seongsu Lee, Seunghyun Oh, Seungjae Moon + 1 more
AI Safety & Privacy Computer Vision Multimodal AI
Nov 9 Speculative Self-Distillation enables Efficient Knowledge Internalization Shayan Talaei, Agam Bhatia, Arshia Soltani Moakhar + 3 more
LLMs & Language Models Efficient AI & Edge
Nov 9 Benchmarking language models and agents for scientific reasoning in evolving materials laboratories Xuyu Dong, Yixuan Li, Jianguo Huang + 5 more
LLMs & Language Models Reasoning & Agents
Nov 9 Scalable Bayesian Optimization for Efficient Exploration of Moire Patterns Panagiotis Krokidas, Christos Lazaridis, Vassilis Sioros + 3 more
ML Theory & Optimization Efficient AI & Edge
Nov 9 Trajectory Density Ratios under Weak Support: A Survey across the Sciences Wei Chen, Lihao Zhuang, Yubing Wu + 1 more
LLMs & Language Models Reasoning & Agents
Nov 9 FireGate: Bounding Behaviour Change Before Training in Continual RL Fine-Tuning Md Anwar Hossen, Ali Jannesari
LLMs & Language Models Efficient AI & Edge
Nov 9 CSG-Nav: Confidence-Aware Semantic-Geometric Fusion for Robust Exploration and Accurate Zero-Shot Object-Goal Navigation Shoubin Chen, Rui Xu, Zehao Wu + 4 more
LLMs & Language Models Reasoning & Agents
Nov 9 MixRoute: Rethinking Single-Distribution Training for Generalizable Neural Routing Hang Yi, Ziwei Huang, Yining Ma + 1 more
LLMs & Language Models ML Theory & Optimization AI Safety & Privacy
Nov 9 AutoQS: Automated Quantization Strategy Design with Large Language Models Zhen Liu, Zhiqin Yang, Yonggang Zhang + 3 more
LLMs & Language Models Efficient AI & Edge RLHF & Alignment
Nov 9 Harness Matters: Measuring and Dissecting Security Resilience in Web Agents Xinyi Wu, Jiagui Chen, JiaYi Dong + 5 more
Reasoning & Agents LLMs & Language Models
Nov 9 Pairwise distortion distribution for compression and quantization Carl Nuzman, Jeongmin Chae, Kursat Rasim Mestav + 1 more
Efficient AI & Edge ML Theory & Optimization
Nov 9 Shaping Useful Noise: Energy Distributions Predict Visual Pretraining Quality Ching Lam Choi, Antonio Torralba, Phillip Isola + 1 more
LLMs & Language Models Computer Vision
Nov 9 Operation-aware Multimodal Clinical Decision Support System for ICU Discharge Risk Assessment Guoqing Zhang, Rafik Hadfi, Takayuki Ito
Reasoning & Agents LLMs & Language Models
Nov 9 BharatSynthQA: A Context-Grounded Question Answering Dataset on Indian Temples and Religious Heritage Riya Naik, Shivam Sharma, Swati Agarwal
LLMs & Language Models Reasoning & Agents
Nov 9 Watching Itself Watch: Self-Auditing Visual Reliance for Video Reasoning Rohan Dugad, Mi Luo, Kristen Grauman
Computer Vision Reasoning & Agents
Nov 9 Decision Aware Origin-Destination Demand Estimation with Structurally Constrained Data Xianzhe Wang, Yueyue Fan, Johannes Royset
RLHF & Alignment ML Theory & Optimization
Nov 9 Scale-Consistent Monocular Fisheye Visual Odometry via Spherical Bundle Adjustment-Guided Unsupervised Depth Learning Wanhui Luo, Hongbo Zhao, Yi Zhou + 3 more
Computer Vision Generative AI & Diffusion
Nov 9 Late but Valuable: Why Deadlines Change the Measured Value of LLM Reasoning Sina Barazandeh, Benjamin E. Lundell, Jose Lugo-Martinez
LLMs & Language Models Reasoning & Agents Efficient AI & Edge
Nov 9 Layer Roles Matter: Mitigating Modality Imbalance in Multimodal Emotion Reasoning via Adaptive Layer Profiling Pengyu Huang, Peipei Song, Beier Zhu + 3 more
LLMs & Language Models Reasoning & Agents
Nov 9 RBA: A Read-out Basis Adapter for Parameter-Efficient Interactive OCTA Vessel Segmentation with SEEM Jaafar M. Al-Ghabban, Mohammad Reza Mohammadi
Efficient AI & Edge LLMs & Language Models ML Theory & Optimization
Nov 9 When Answer Decodability Is Not a Decision: Separating Final-Answer and Imminent-Emission Signals in Chain-of-Thought Hyojung Han, Jongmin Kim, Seung-Hun Jeon
Reasoning & Agents LLMs & Language Models
Nov 9 How Many Candidates Does a One-Step World Model Need? A Random-Codebook Account of Nearest-of-m Training on Frozen DINO Tokens Yong Hwi Song, Keon Myung Lee
Generative AI & Diffusion Reasoning & Agents Efficient AI & Edge