{"total":139,"rows":[{"id":"2603.22435","title":"CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation","created":"2026-03-23","cited_by_count":88,"area":"vla"},{"id":"2603.02115","title":"Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons","created":"2026-03-02","cited_by_count":60,"area":"alignment"},{"id":"2605.02881","title":"MolmoAct2: Action Reasoning Models for Real-world Deployment","created":"2026-05-04","cited_by_count":50,"area":"lr"},{"id":"2605.25979","title":"LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence","created":"2026-05-25","cited_by_count":39,"area":"mllm"},{"id":"2603.28069","title":"MolmoPoint: Better Pointing for VLMs with Grounding Tokens","created":"2026-03-30","cited_by_count":15,"area":"mllm"},{"id":"2605.09874","title":"EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding","created":"2026-05-11","cited_by_count":13,"area":"lr"},{"id":"2604.10577","title":"The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents","created":"2026-04-12","cited_by_count":12,"area":"agents"},{"id":"2602.00288","title":"TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs","created":"2026-01-30","cited_by_count":11,"area":null},{"id":"2602.08828","title":"VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning","created":"2026-02-09","cited_by_count":11,"area":"lr"},{"id":"2604.04917","title":"Vero: An Open RL Recipe for General Visual Reasoning","created":"2026-04-06","cited_by_count":11,"area":"lr"},{"id":"2607.14935","title":"VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding","created":"2026-07-16","cited_by_count":10,"area":null},{"id":"2607.24904","title":"Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model","created":"2026-07-27","cited_by_count":10,"area":"lr"},{"id":"2606.09393","title":"CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning","created":"2026-06-08","cited_by_count":8,"area":"mllm"},{"id":"2602.06566","title":"SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs","created":"2026-02-06","cited_by_count":7,"area":"lr"},{"id":"2603.06569","title":"Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders","created":"2026-03-06","cited_by_count":7,"area":"mllm"},{"id":"2604.01569","title":"VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification","created":"2026-04-02","cited_by_count":7,"area":"mllm"},{"id":"2606.02569","title":"AdaCodec: A Predictive Visual Code for Video MLLMs","created":"2026-06-01","cited_by_count":7,"area":null},{"id":"2603.12703","title":"SVCBench: A Streaming Video Counting Benchmark for Spatial-Temporal State Maintenance","created":"2026-03-13","cited_by_count":6,"area":null},{"id":"2606.11324","title":"Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models","created":"2026-06-09","cited_by_count":6,"area":"lr"},{"id":"2604.08120","title":"Small Vision-Language Models are Smart Compressors for Long Video Understanding","created":"2026-04-09","cited_by_count":5,"area":"mllm"},{"id":"2606.12195","title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","created":"2026-06-10","cited_by_count":5,"area":"agents"},{"id":"2606.18558","title":"MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction","created":"2026-06-17","cited_by_count":5,"area":null},{"id":"2603.24575","title":"VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models","created":"2026-03-25","cited_by_count":4,"area":null},{"id":"2603.26653","title":"PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning","created":"2026-03-27","cited_by_count":4,"area":"lr"},{"id":"2605.00444","title":"Scaling Video Understanding via Compact Latent Multi-Agent Collaboration","created":"2026-05-01","cited_by_count":4,"area":"mllm"},{"id":"2605.18984","title":"Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos","created":"2026-05-18","cited_by_count":4,"area":null},{"id":"2606.28864","title":"On Test-Time Scaling for Vision-Language Models","created":"2026-06-27","cited_by_count":4,"area":"lr"},{"id":"2608.20492","title":"Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs","created":"2026-08-20","cited_by_count":4,"area":"lr"},{"id":"2603.08436","title":"Can Vision-Language Models Solve the Shell Game?","created":"2026-03-09","cited_by_count":3,"area":"mllm"},{"id":"2603.10178","title":"Video-Based Reward Modeling for Computer-Use Agents","created":"2026-03-10","cited_by_count":3,"area":"agents"},{"id":"2603.16506","title":"VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations","created":"2026-03-17","cited_by_count":3,"area":"lr"},{"id":"2603.18373","title":"To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2603.18892","title":"MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model","created":"2026-03-19","cited_by_count":3,"area":"lr"},{"id":"2603.25021","title":"VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning","created":"2026-03-26","cited_by_count":3,"area":"lr"},{"id":"2605.16079","title":"VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation","created":"2026-05-15","cited_by_count":3,"area":"mllm"},{"id":"2606.00828","title":"RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes","created":"2026-05-30","cited_by_count":3,"area":"mllm"},{"id":"2607.05150","title":"Claim-Level Rubric Rewards for Video Caption Reinforcement Learning","created":"2026-07-06","cited_by_count":3,"area":"alignment"},{"id":"2607.11270","title":"Towards Predictive, Aligned, and Scalable Robot Learning","created":"2026-07-13","cited_by_count":3,"area":"wm"},{"id":"2607.17423","title":"TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs","created":"2026-07-19","cited_by_count":3,"area":"mllm"},{"id":"2607.20785","title":"Robostral Navigate","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2603.10652","title":"Are Video Reasoning Models Ready to Go Outside?","created":"2026-03-11","cited_by_count":2,"area":"lr"},{"id":"2604.00677","title":"CL-VISTA: Benchmarking Continual Learning in Video Large Language Models","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2604.24953","title":"ViPO: Visual Preference Optimization at Scale","created":"2026-04-27","cited_by_count":2,"area":"alignment"},{"id":"2605.07415","title":"ChartREG++: Towards Benchmarking and Improving Chart Referring Expression Grounding under Diverse referring clues and Multi-Target Referring","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2605.08560","title":"ZAYA1-VL-8B Technical Report","created":"2026-05-08","cited_by_count":2,"area":"mllm"},{"id":"2606.22694","title":"SATURN: Symbolic Spatial Reasoning for Multi-Perspective Grounding","created":"2026-06-21","cited_by_count":2,"area":"lr"},{"id":"2606.28551","title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","created":"2026-06-26","cited_by_count":2,"area":"mllm"},{"id":"2607.00115","title":"PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking","created":"2026-06-30","cited_by_count":2,"area":"lr"},{"id":"2607.13033","title":"DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation","created":"2026-07-14","cited_by_count":2,"area":"offlinerl"},{"id":"2607.26848","title":"ICDAR 2026 Competition on Information Extraction from Atomic Layer Deposition/Etching (ALD/E) Scientific Figures","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2602.10639","title":"VideoSTF: Stress-Testing Output Repetition in Video Large Language Models","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.10978","title":"GroundCount: Grounding Vision-Language Models with Object Detection for Mitigating Counting Hallucinations","created":"2026-03-11","cited_by_count":1,"area":"lr"},{"id":"2603.12147","title":"EgoIntent: A Pre-Outcome Micro-Step Benchmark for Understanding What, Why, and Next","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2603.18004","title":"Unified Spatio-Temporal Token Scoring for Efficient Video VLMs","created":"2026-03-18","cited_by_count":1,"area":"mllm"},{"id":"2604.11038","title":"EgoFun3D: Modeling Interactive Objects from Egocentric Videos using Function Templates","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.12119","title":"Beyond Perception Errors: Semantic Fixation in Large Vision-Language Models","created":"2026-04-13","cited_by_count":1,"area":"mllm"},{"id":"2604.21873","title":"Grounding Video Reasoning in Physical Signals","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2604.22226","title":"Towards Temporal Compositional Reasoning in Long-Form Sports Videos","created":"2026-04-24","cited_by_count":1,"area":"lr"},{"id":"2605.05955","title":"TableVista: Benchmarking Multimodal Table Reasoning under Visual and Structural Complexity","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.10887","title":"Count Anything at Any Granularity","created":"2026-05-11","cited_by_count":1,"area":"mllm"},{"id":"2605.19075","title":"CRAFT: Critic-Refined Adaptive Key-Frame Targeting for Multimodal Video Question Answering","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.21954","title":"MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues","created":"2026-05-21","cited_by_count":1,"area":"mllm"},{"id":"2605.21988","title":"Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2605.23826","title":"Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2605.31529","title":"SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence","created":"2026-05-29","cited_by_count":1,"area":"agents"},{"id":"2606.03920","title":"Benchmarking Visual State Tracking in Multimodal Video Understanding","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.03988","title":"Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2606.05758","title":"DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models","created":"2026-06-04","cited_by_count":1,"area":"mllm"},{"id":"2606.29531","title":"MotionAtlas: Detailed Region Captioning for Motion-Centric Videos","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2607.01117","title":"MoHallBench: A Benchmark for Motion Hallucination in Video Large Language Models","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2607.12711","title":"MaxSAT-Based Feedback for Guiding Vision-Language Models in Sudoku","created":"2026-07-14","cited_by_count":1,"area":"lr"},{"id":"2607.13454","title":"GeoAnchor: Collaborative Reasoning via Latent Decomposition for 3D Spatial Understanding","created":"2026-07-15","cited_by_count":1,"area":"lr"},{"id":"2608.03160","title":"Caved or Convinced: Temporal Sampling Gates Claim Deference in Video Large Language Models","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.05707","title":"One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding","created":"2026-08-06","cited_by_count":1,"area":"mllm"},{"id":"2608.17402","title":"MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding","created":"2026-08-18","cited_by_count":1,"area":"mllm"},{"id":"2608.23435","title":"Towards Comprehensive Basketball Understanding","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2608.26517","title":"HUG-VIS: A Multimodal Benchmark for Human-centered Understanding and Generation in Visual Intelligence","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2608.30935","title":"LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2609.00746","title":"Text Capability Loss in Vision-Language Adaptation: An Attention-Sink Diagnosis","created":"2026-09-01","cited_by_count":1,"area":"lr"},{"id":"2609.04203","title":"Temporal Self-Distillation: Learning Visual State Tracking in Videos Without Supervision","created":"2026-09-03","cited_by_count":1,"area":"distill"},{"id":"2609.14080","title":"Adapting Open-Weight MLLMs to Generate Point Prompts for Electron Microscopy Segmentation","created":"2026-09-12","cited_by_count":1,"area":null},{"id":"2609.23139","title":"QwenVLConnector: A Fast, Unified Medical VLM Chatbot for Fine-Grained Clinical Perception and Text Generation","created":"2026-09-19","cited_by_count":1,"area":"mllm"},{"id":"2601.14121","title":"NewsRECON: News Article Retrieval for Image Contextualization","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2602.10384","title":"When Tables Go Crazy: Evaluating Multimodal Models on French Financial Documents","created":"2026-02-11","cited_by_count":0,"area":"mllm"},{"id":"2602.10771","title":"From Steering to Pedalling: Do Autonomous Driving VLMs Generalize to Cyclist-Assistive Spatial Perception and Planning?","created":"2026-02-11","cited_by_count":0,"area":"driving"},{"id":"2603.14579","title":"Medical Image Spatial Grounding with Semantic Sampling","created":"2026-03-15","cited_by_count":0,"area":"mllm"},{"id":"2603.20354","title":"Leum-VL Technical Report","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.21746","title":"Getting to the Point: Pointing Improves LVLMs at Counting","created":"2026-03-23","cited_by_count":0,"area":"lr"},{"id":"2604.02338","title":"LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning","created":"2026-02-01","cited_by_count":0,"area":"moe"},{"id":"2604.04415","title":"STEER: Structured Event Evidence for Video Reasoning via Multi-Objective Reinforcement Learning","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2604.08522","title":"UniversalVTG: A Universal and Lightweight Foundation Model for Video Temporal Grounding","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.09037","title":"SiMing-Bench: Evaluating Procedural Correctness from Continuous Interactions in Clinical Skill Videos","created":"2026-04-10","cited_by_count":0,"area":"mllm"},{"id":"2604.21343","title":"Latent Denoising Improves Visual Alignment in Large Multimodal Models","created":"2026-04-23","cited_by_count":0,"area":"mllm"},{"id":"2605.08452","title":"NICE FACT: Diagnosing and Calibrating VLMs in Quantitative Reasoning for Kinematic Physics","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.13080","title":"Learning to See What You Need: Gaze Attention for Multimodal Large Language Models","created":"2026-05-13","cited_by_count":0,"area":"mllm"},{"id":"2605.13223","title":"Skill-Aligned Annotation for Reliable Evaluation in Text-to-Image Generation","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.17823","title":"Why We Look Where We Look: Emergent Human-like Fixations of a Foveated Visual Language Model Maximizing Scene Understanding","created":"2026-05-18","cited_by_count":0,"area":"mllm"},{"id":"2605.22185","title":"Enhancing Multimodal Large Language Models for Safety-Critical Driving Video Analysis","created":"2026-05-21","cited_by_count":0,"area":"mllm"},{"id":"2605.24291","title":"Rubato: Transcribing Piano Music with Timestamps","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.00390","title":"Zamba2-VL Technical Report","created":"2026-05-29","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}