{"total":63,"rows":[{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518,"area":null},{"id":"2505.05467","title":"StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant","created":"2025-05-08","cited_by_count":63,"area":null},{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59,"area":null},{"id":"2506.15220","title":"video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language Models","created":"2025-06-18","cited_by_count":47,"area":null},{"id":"2503.09146","title":"Generative Frame Sampler for Long Video Understanding","created":"2025-03-12","cited_by_count":37,"area":null},{"id":"2503.18943","title":"SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding","created":"2025-03-24","cited_by_count":30,"area":null},{"id":"2506.10821","title":"VideoExplorer: Think With Videos For Agentic Long-Video Understanding","created":"2025-06-12","cited_by_count":29,"area":null},{"id":"2503.19903","title":"Scaling Vision Pre-Training to 4K Resolution","created":"2025-03-25","cited_by_count":28,"area":null},{"id":"2504.16082","title":"MR. Video: \"MapReduce\" is the Principle for Long Video Understanding","created":"2025-04-22","cited_by_count":23,"area":null},{"id":"2507.18342","title":"EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs","created":"2025-07-24","cited_by_count":23,"area":null},{"id":"2503.08507","title":"Referring to Any Person","created":"2025-03-11","cited_by_count":21,"area":null},{"id":"2503.14378","title":"Impossible Videos","created":"2025-03-18","cited_by_count":16,"area":null},{"id":"2509.12618","title":"ActiveVLN: Towards Active Exploration via Multi-Turn RL in Vision-and-Language Navigation","created":"2025-09-16","cited_by_count":13,"area":null},{"id":"2602.15329","title":"EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use","created":"2026-02-17","cited_by_count":12,"area":null},{"id":"2510.14256","title":"Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning","created":"2025-10-16","cited_by_count":10,"area":null},{"id":"2505.23484","title":"VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation","created":"2025-05-29","cited_by_count":9,"area":null},{"id":"2603.20422","title":"PEARL: Personalized Streaming Video Understanding Model","created":"2026-03-20","cited_by_count":9,"area":null},{"id":"2506.03126","title":"AnimeShooter: A Multi-Shot Animation Dataset for Reference-Guided Video Generation","created":"2025-06-03","cited_by_count":8,"area":null},{"id":"2512.08639","title":"Aerial Vision-Language Navigation with a Unified Framework for Spatial, Temporal and Embodied Reasoning","created":"2025-12-09","cited_by_count":8,"area":null},{"id":"2512.03575","title":"UniComp: Rethinking Video Compression Through Informational Uniqueness","created":"2025-12-03","cited_by_count":7,"area":null},{"id":"2504.06835","title":"LVC: A Lightweight Compression Framework for Enhancing VLMs in Long Video Understanding","created":"2025-04-09","cited_by_count":6,"area":null},{"id":"2508.19650","title":"Video-LevelGauge: Investigating Contextual Positional Bias in Large Video Language Models","created":"2025-08-27","cited_by_count":6,"area":null},{"id":"2511.17490","title":"Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination","created":"2025-11-21","cited_by_count":6,"area":null},{"id":"2602.07960","title":"D-ORCA: Dialogue-Centric Optimization for Robust Audio-Visual Captioning","created":"2026-02-08","cited_by_count":6,"area":null},{"id":"2510.20622","title":"SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding","created":"2025-10-23","cited_by_count":5,"area":null},{"id":"2512.12622","title":"D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation","created":"2025-12-14","cited_by_count":5,"area":null},{"id":"2601.18188","title":"\\textsc{NaVIDA}: Vision-Language Navigation with Inverse Dynamics Augmentation","created":"2026-01-26","cited_by_count":5,"area":null},{"id":"2509.20851","title":"Poisoning Prompt-Guided Sampling in Video Large Language Models","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2511.07299","title":"VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2602.00222","title":"MapDream: Task-Driven Map Learning for Vision-Language Navigation","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2506.07811","title":"Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2510.12444","title":"A Review of Longitudinal Radiology Report Generation: Dataset Composition, Methods, and Performance Evaluation","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2511.20620","title":"Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2503.09279","title":"Cockatiel: Ensembling Synthetic and Human Preferenced Training for Detailed Video Caption","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2506.02308","title":"MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2508.13692","title":"HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2511.20190","title":"SFA: Scan, Focus, and Amplify toward Guidance-aware Answering for Video TextVQA","created":"2025-11-25","cited_by_count":2,"area":null},{"id":"2605.11722","title":"EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.22823","title":"Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs","created":"2026-05-21","cited_by_count":2,"area":null},{"id":"2508.16942","title":"HieroAction: Hierarchically Guided VLM for Fine-Grained Action Analysis","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2512.11534","title":"HFS: Holistic Query-Aware Frame Selection for Efficient Video Understanding","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2601.02908","title":"TA-Prompting: Enhancing Video Large Language Models for Dense Video Captioning via Temporal Anchors","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2601.16471","title":"Order from Chaos: Physical World Understanding from Glitchy Gameplay Videos","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2605.06809","title":"LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.07593","title":"TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2606.24602","title":"ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2507.22369","title":"Exploring the Application of Visual Question Answering (VQA) for Classroom Activity Monitoring","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2602.04233","title":"Provable Target Sample Complexity Improvements as Pre-Trained Models Scale","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.09255","title":"STaR: Scalable Task-Conditioned Retrieval for Long-Horizon Multimodal Robot Memory","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.00126","title":"QuickGrasp: Responsive Video-Language Querying Service via Accelerated Tokenization and Edge-Augmented Inference","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.22453","title":"XNote: Benchmarking Automated Community Notes Generation for Image-based Contextual Deception","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2606.00746","title":"Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.03635","title":"VidMsg: A Benchmark for Implicit Message Inference in Short Videos","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.16470","title":"Decoupled Object-Centric Video Understanding for Generating Robotic Manipulation Commands","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.24477","title":"video-SALMONN-R$^3$: Learning to ReWatch, ReAsk, and ReAnswer for Efficient Video Understanding","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.09488","title":"SigLIP-HD by Fine-to-Coarse Supervision","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2608.05747","title":"GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.05780","title":"Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.04242","title":"Training-Free Speech-Centric Omni Understanding with Frozen VLMs","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.07941","title":"ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.10355","title":"Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.35473","title":"Handwritten Text Recognition Lives in the High-Pixel Variance Subspace","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.16299","title":"Learning Temporal Evidence Selection for Video Anomaly Understanding","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}