{"total":92,"rows":[{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809,"area":"wm"},{"id":"2601.10611","title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","created":"2026-01-15","cited_by_count":139,"area":"mllm"},{"id":"2603.14482","title":"V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning","created":"2026-03-15","cited_by_count":117,"area":null},{"id":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","cited_by_count":89,"area":null},{"id":"2512.10794","title":"What matters for Representation Alignment: Global Information or Spatial Structure?","created":"2025-12-11","cited_by_count":84,"area":null},{"id":"2512.10942","title":"VL-JEPA: Joint Embedding Predictive Architecture for Vision-language","created":"2025-12-11","cited_by_count":68,"area":"mllm"},{"id":"2510.17269","title":"FineVision: Open Data Is All You Need","created":"2025-10-20","cited_by_count":53,"area":"mllm"},{"id":"2510.20579","title":"Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence","created":"2025-10-23","cited_by_count":49,"area":"lr"},{"id":"2602.14486","title":"Revisiting the Platonic Representation Hypothesis: An Aristotelian View","created":"2026-02-16","cited_by_count":44,"area":null},{"id":"2509.02722","title":"Planning with Reasoning using Vision Language World Model","created":"2025-09-02","cited_by_count":36,"area":"wm"},{"id":"2506.09943","title":"CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models","created":"2025-06-11","cited_by_count":35,"area":"lr"},{"id":"2506.03340","title":"Seeing the Arrow of Time in Large Multimodal Models","created":"2025-06-03","cited_by_count":30,"area":"mllm"},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2506.05349","title":"VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos","created":"2025-06-05","cited_by_count":25,"area":"lr"},{"id":"2510.18876","title":"Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs","created":"2025-10-21","cited_by_count":18,"area":"mllm"},{"id":"2510.03506","title":"OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows","created":"2025-10-03","cited_by_count":17,"area":null},{"id":"2510.06077","title":"When Thinking Drifts: Evidential Grounding for Robust Video Reasoning","created":"2025-10-07","cited_by_count":16,"area":null},{"id":"2602.00462","title":"LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs","created":"2026-01-31","cited_by_count":15,"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":"2510.12225","title":"HoneyBee: Data Recipes for Vision-Language Reasoners","created":"2025-10-14","cited_by_count":13,"area":"lr"},{"id":"2512.19687","title":"Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning","created":"2025-12-22","cited_by_count":13,"area":null},{"id":"2606.13674","title":"RepWAM: World Action Modeling with Representation Visual-Action Tokenizers","created":"2026-06-11","cited_by_count":13,"area":"wm"},{"id":"2601.10592","title":"Action100M: A Large-scale Video Action Dataset","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2601.16093","title":"SAMTok: Representing Any Mask with Two Words","created":"2026-01-22","cited_by_count":11,"area":null},{"id":"2602.00288","title":"TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs","created":"2026-01-30","cited_by_count":11,"area":null},{"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":"2510.02292","title":"From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens","created":"2025-10-02","cited_by_count":9,"area":"mllm"},{"id":"2506.06277","title":"ExAct: A Video-Language Benchmark for Expert Action Analysis","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2512.14273","title":"Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-in","created":"2025-12-16","cited_by_count":8,"area":null},{"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":"2606.02569","title":"AdaCodec: A Predictive Visual Code for Video MLLMs","created":"2026-06-01","cited_by_count":7,"area":null},{"id":"2509.03501","title":"Strefer: Empowering Video LLMs with Space-Time Referring and Reasoning via Synthetic Instruction Data","created":"2025-09-03","cited_by_count":6,"area":"lr"},{"id":"2511.18452","title":"NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering","created":"2025-11-23","cited_by_count":6,"area":null},{"id":"2512.10927","title":"FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos","created":"2025-12-11","cited_by_count":5,"area":"lr"},{"id":"2512.23592","title":"Same or Not? Enhancing Visual Perception in Vision-Language Models","created":"2025-12-29","cited_by_count":5,"area":"mllm"},{"id":"2511.17481","title":"Counterfactual World Models via Digital Twin-conditioned Video Diffusion","created":"2025-11-21","cited_by_count":4,"area":"wm"},{"id":"2603.14659","title":"VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting","created":"2026-03-15","cited_by_count":4,"area":"distill"},{"id":"2603.18856","title":"Motion-o: Trajectory-Grounded Video Reasoning","created":"2026-03-19","cited_by_count":4,"area":"lr"},{"id":"2603.25864","title":"GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Tasks","created":"2026-03-26","cited_by_count":4,"area":null},{"id":"2604.12896","title":"Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs","created":"2026-04-14","cited_by_count":4,"area":"lr"},{"id":"2604.24317","title":"Don't Pause! Every prediction matters in a streaming video","created":"2026-04-27","cited_by_count":4,"area":null},{"id":"2606.07433","title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","created":"2026-06-05","cited_by_count":4,"area":"lr"},{"id":"2510.06529","title":"VUGEN: Visual Understanding priors for GENeration","created":"2025-10-08","cited_by_count":3,"area":"mllm"},{"id":"2601.01095","title":"NarrativeTrack: Evaluating Entity-Centric Reasoning for Narrative Understanding","created":"2026-01-03","cited_by_count":3,"area":"lr"},{"id":"2602.03230","title":"EventFlash: Towards Efficient MLLMs for Event-Based Vision","created":"2026-02-03","cited_by_count":3,"area":"mllm"},{"id":"2602.13195","title":"Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervision","created":"2026-02-13","cited_by_count":3,"area":null},{"id":"2603.08436","title":"Can Vision-Language Models Solve the Shell Game?","created":"2026-03-09","cited_by_count":3,"area":"mllm"},{"id":"2604.21718","title":"Building a Precise Video Language with Human-AI Oversight","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2511.12207","title":"Mixture of States: Routing Token-Level Dynamics for Multimodal Generation","created":"2025-11-15","cited_by_count":2,"area":"diffusion"},{"id":"2605.08560","title":"ZAYA1-VL-8B Technical Report","created":"2026-05-08","cited_by_count":2,"area":"mllm"},{"id":"2606.25634","title":"SSMNBench: Diagnosing Image-based Cross-View Human-Object Understanding via Single-View Sufficiency and Multi-View Necessity","created":"2026-06-24","cited_by_count":2,"area":"mllm"},{"id":"2606.28551","title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","created":"2026-06-26","cited_by_count":2,"area":"mllm"},{"id":"2506.05440","title":"BYO-Eval: Build Your Own Dataset for Fine-Grained Visual Assessment of Multimodal Language Models","created":"2025-06-05","cited_by_count":1,"area":"mllm"},{"id":"2509.12146","title":"Multi Anatomy X-Ray Foundation Model","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2511.07413","title":"DigiData: Training and Evaluating General-Purpose Mobile Control Agents","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2511.18448","title":"EventBench: Towards Comprehensive Benchmarking of Event-based MLLMs","created":"2025-11-23","cited_by_count":1,"area":"mllm"},{"id":"2511.20770","title":"Text-Guided Semantic Image Encoder","created":"2025-11-25","cited_by_count":1,"area":"mllm"},{"id":"2603.18004","title":"Unified Spatio-Temporal Token Scoring for Efficient Video VLMs","created":"2026-03-18","cited_by_count":1,"area":"mllm"},{"id":"2603.18453","title":"Learning Consistent Temporal Grounding between Related Tasks in Sports Coaching","created":"2026-03-19","cited_by_count":1,"area":null},{"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":"2606.25842","title":"Graph it first! Enabling Reasoning on Long-form Egocentric Videos through Scene Graphs","created":"2026-06-24","cited_by_count":1,"area":"lr"},{"id":"2606.29531","title":"MotionAtlas: Detailed Region Captioning for Motion-Centric Videos","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2608.03147","title":"CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation","created":"2026-08-04","cited_by_count":1,"area":null},{"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":"2609.27252","title":"What Converges in the Platonic Representation Hypothesis? Structure over Geometry","created":"2026-09-23","cited_by_count":1,"area":null},{"id":"2507.21353","title":"Group Relative Augmentation for Data Efficient Action Detection","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2511.03768","title":"What's in Common? Multimodal Models Hallucinate When Reasoning Across Scenes","created":"2025-11-05","cited_by_count":0,"area":"lr"},{"id":"2512.10607","title":"Track and Caption Any Motion: Open-Vocabulary Spatiotemporal Captioning via Trajectory-Conditioned Generation","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2602.01915","title":"VLM-Guided Experience Replay","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"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":"2602.17260","title":"EA-Swin: An Embedding-Agnostic Swin Transformer for AI-Generated Video Detection","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.01096","title":"Unified Vision-Language Modeling via Concept Space Alignment","created":"2026-03-01","cited_by_count":0,"area":"mllm"},{"id":"2603.25145","title":"Learning to Rank Caption Chains for Video-Text Alignment","created":"2026-03-26","cited_by_count":0,"area":"alignment"},{"id":"2604.08762","title":"InstrAct: Towards Action-Centric Understanding in Instructional Videos","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.12074","title":"BARISTA: A Multi-Task Egocentric Benchmark for Compositional Visual Understanding","created":"2026-05-12","cited_by_count":0,"area":null},{"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":"2605.19130","title":"EgoBabyVLM: Benchmarking Cross-Modal Learning from Naturalistic Egocentric Video Data","created":"2026-05-18","cited_by_count":0,"area":"mllm"},{"id":"2605.21625","title":"Flat-Pack Bench: Evaluating Spatio-Temporal Understanding in Large Vision-Language Models through Furniture Assembly","created":"2026-05-20","cited_by_count":0,"area":"mllm"},{"id":"2606.00390","title":"Zamba2-VL Technical Report","created":"2026-05-29","cited_by_count":0,"area":"mllm"},{"id":"2606.02273","title":"Vision-language Models for Driver Monitoring Systems: A Driver Activity Description Dataset","created":"2026-06-01","cited_by_count":0,"area":"mllm"},{"id":"2606.19096","title":"PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.19100","title":"AMALIA-VL: A Native European Portuguese Open-Source Vision and Language Model","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.30288","title":"VisReflect: Latent Visual Reflection for Fine-Grained Perception in Long Visual Context","created":"2026-06-29","cited_by_count":0,"area":"mllm"},{"id":"2607.12304","title":"What Does a Temporal Benchmark Score Measure? Decomposing Channel Use in Video VLM Evaluation","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2608.15802","title":"PWLR: Pairwise Witness Local Rejection for Boundary-Aware Out-of-Distribution Detection","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.18602","title":"Teach a Molmo2Fish: Towards interactive fish tracking with natural language guidance","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.11126","title":"Beyond Benchmarks: Using VLMs to Reveal Systematic Classification Failures Under Real World Conditions","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.31823","title":"SynDORBench: Evaluating LVLM Perceptual Robustness Under Physically Constrained Visibility Conditions","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.39588","title":"KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMs","created":"2026-09-30","cited_by_count":0,"area":"mllm"},{"id":"2610.16118","title":"Elephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding","created":"2026-10-12","cited_by_count":0,"area":"mllm"},{"id":"2610.17355","title":"WIRE: Weight Space Implicit Representation Encoding of Frozen Video LLMs","created":"2026-10-12","cited_by_count":0,"area":"inference"},{"id":"2610.18535","title":"Meta-Video: Efficient Standardized Evaluation for Video Understanding","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}