{"total":97,"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":"2501.05510","title":"OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?","created":"2025-01-09","cited_by_count":142,"area":null},{"id":"2501.12380","title":"MMVU: Measuring Expert-Level Multi-Discipline Video Understanding","created":"2025-01-21","cited_by_count":137,"area":null},{"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":"2412.07755","title":"SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models","created":"2024-12-10","cited_by_count":114,"area":"mllm"},{"id":"2412.10360","title":"Apollo: An Exploration of Video Understanding in Large Multimodal Models","created":"2024-12-13","cited_by_count":89,"area":"mllm"},{"id":"2501.07888","title":"Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding","created":"2025-01-14","cited_by_count":81,"area":"mllm"},{"id":"2511.20785","title":"LongVT: Incentivizing \"Thinking with Long Videos\" via Native Tool Calling","created":"2025-11-25","cited_by_count":61,"area":"lr"},{"id":"2606.13392","title":"MiniMax Sparse Attention","created":"2026-06-11","cited_by_count":44,"area":"lr"},{"id":"2504.14693","title":"Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark","created":"2025-04-20","cited_by_count":37,"area":null},{"id":"2503.19951","title":"Audio-centric Video Understanding Benchmark without Text Shortcut","created":"2025-03-25","cited_by_count":36,"area":"mllm"},{"id":"2503.17489","title":"Judge Anything: MLLM as a Judge Across Any Modality","created":"2025-03-21","cited_by_count":34,"area":null},{"id":"2505.00681","title":"MINERVA: Evaluating Complex Video Reasoning","created":"2025-05-01","cited_by_count":32,"area":"lr"},{"id":"2412.16211","title":"Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generation","created":"2024-12-17","cited_by_count":30,"area":null},{"id":"2506.03340","title":"Seeing the Arrow of Time in Large Multimodal Models","created":"2025-06-03","cited_by_count":30,"area":"mllm"},{"id":"2506.09987","title":"A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs","created":"2025-06-11","cited_by_count":30,"area":"lr"},{"id":"2507.09313","title":"ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models","created":"2025-07-12","cited_by_count":27,"area":null},{"id":"2512.22315","title":"VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoning","created":"2025-12-26","cited_by_count":27,"area":"lr"},{"id":"2503.13956","title":"Improving LLM Video Understanding with 16 Frames Per Second","created":"2025-03-18","cited_by_count":26,"area":"mllm"},{"id":"2507.15028","title":"Towards Video Thinking Test: A Holistic Benchmark for Advanced Video Reasoning and Understanding","created":"2025-07-20","cited_by_count":24,"area":"lr"},{"id":"2503.23452","title":"VideoGen-Eval: Agent-based System for Video Generation Evaluation","created":"2025-03-30","cited_by_count":23,"area":"agents"},{"id":"2506.07180","title":"Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs","created":"2025-06-08","cited_by_count":21,"area":"lr"},{"id":"2512.02231","title":"See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models","created":"2025-12-01","cited_by_count":20,"area":"mllm"},{"id":"2505.22457","title":"Fostering Video Reasoning via Next-Event Prediction","created":"2025-05-28","cited_by_count":18,"area":"lr"},{"id":"2505.24867","title":"Time Blindness: Why Video-Language Models Can't See What Humans Can?","created":"2025-05-30","cited_by_count":18,"area":"mllm"},{"id":"2501.10674","title":"Can Multimodal LLMs do Visual Temporal Understanding and Reasoning? The answer is No!","created":"2025-01-18","cited_by_count":15,"area":"lr"},{"id":"2508.01699","title":"TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding","created":"2025-08-03","cited_by_count":14,"area":"moe"},{"id":"2509.08621","title":"AdsQA: Towards Advertisement Video Understanding","created":"2025-09-10","cited_by_count":13,"area":null},{"id":"2505.20715","title":"MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding","created":"2025-05-27","cited_by_count":12,"area":"mllm"},{"id":"2512.04451","title":"StreamEQA: Towards Streaming Video Understanding for Embodied Scenarios","created":"2025-12-04","cited_by_count":12,"area":null},{"id":"2412.02071","title":"Progress-Aware Video Frame Captioning","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2503.18923","title":"Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models","created":"2025-03-24","cited_by_count":11,"area":null},{"id":"2510.02295","title":"VideoNSA: Native Sparse Attention Scales Video Understanding","created":"2025-10-02","cited_by_count":11,"area":"mllm"},{"id":"2602.00288","title":"TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs","created":"2026-01-30","cited_by_count":11,"area":null},{"id":"2411.09105","title":"VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models","created":"2024-11-14","cited_by_count":10,"area":null},{"id":"2508.11576","title":"Causality Matters: How Temporal Information Emerges in Video Language Models","created":"2025-08-15","cited_by_count":10,"area":null},{"id":"2505.20124","title":"TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos","created":"2025-05-26","cited_by_count":9,"area":null},{"id":"2507.16878","title":"CausalStep: A Benchmark for Explicit Stepwise Causal Reasoning in Videos","created":"2025-07-22","cited_by_count":9,"area":"lr"},{"id":"2412.03565","title":"INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning","created":"2024-12-04","cited_by_count":8,"area":"mllm"},{"id":"2507.09491","title":"GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them?","created":"2025-07-13","cited_by_count":8,"area":"lr"},{"id":"2506.08708","title":"PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly","created":"2025-06-10","cited_by_count":7,"area":"mllm"},{"id":"2605.27074","title":"IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams","created":"2026-05-26","cited_by_count":7,"area":"mllm"},{"id":"2505.08455","title":"VCRBench: Exploring Long-form Causal Reasoning Capabilities of Large Video Language Models","created":"2025-05-13","cited_by_count":5,"area":"lr"},{"id":"2501.05711","title":"From My View to Yours: Learning Egocentric Cues from Exocentric Video using Privileged Egocentric Supervision","created":"2025-01-10","cited_by_count":4,"area":"mllm"},{"id":"2507.23284","title":"Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval","created":"2025-07-31","cited_by_count":4,"area":"mllm"},{"id":"2605.13803","title":"EvoGround: Self-Evolving Video Agents for Video Temporal Grounding","created":"2026-05-13","cited_by_count":4,"area":null},{"id":"2605.19846","title":"FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding","created":"2026-05-19","cited_by_count":4,"area":"mllm"},{"id":"2503.18712","title":"LLaVAction: evaluating and training multi-modal large language models for action understanding","created":"2025-03-24","cited_by_count":3,"area":"mllm"},{"id":"2509.01167","title":"TempCore: Are Video QA Benchmarks Temporally Grounded?","created":"2025-09-01","cited_by_count":3,"area":"mllm"},{"id":"2509.24563","title":"NeMo: Needle in a Montage for Video-Language Understanding","created":"2025-09-29","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":"2605.30346","title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","created":"2026-05-28","cited_by_count":3,"area":"wm"},{"id":"2502.20811","title":"HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models","created":"2025-02-28","cited_by_count":2,"area":"mllm"},{"id":"2503.18637","title":"Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2503.24008","title":"H2VU-Benchmark: A Comprehensive Benchmark for Hierarchical Holistic Video Understanding","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2506.00928","title":"Deep Temporal Reasoning in Video Language Models: A Cross-Linguistic Evaluation of Action Duration and Completion through Perfect Times","created":"2025-06-01","cited_by_count":2,"area":"lr"},{"id":"2512.05277","title":"From Segments to Scenes: Temporal Understanding for Agentic Autonomous Driving via Vision-Language Models","created":"2025-12-04","cited_by_count":2,"area":"mllm"},{"id":"2602.14705","title":"It's a Matter of Time: Three Lessons on Long-Term Motion for Perception","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2603.07071","title":"VirtueBench: Evaluating Trustworthiness under Uncertainty in Long Video Understanding","created":"2026-03-07","cited_by_count":2,"area":"mllm"},{"id":"2603.17693","title":"Learning Transferable Temporal Primitives for Video Reasoning via Synthetic Videos","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2604.01460","title":"Reinforcing Consistency in Video MLLMs with Structured Rewards","created":"2026-04-01","cited_by_count":2,"area":"mllm"},{"id":"2605.13737","title":"Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2607.13792","title":"EgoProceVQA: A Novel Egocentric Procedural Understanding Task with Self-Skill-Exploration Agent","created":"2026-07-15","cited_by_count":2,"area":"agents"},{"id":"2412.11391","title":"Temporal Contrastive Learning for Video Temporal Reasoning in Large Vision-Language Models","created":"2024-12-16","cited_by_count":1,"area":"lr"},{"id":"2505.19125","title":"RTime-QA: A Benchmark for Atomic Temporal Event Understanding in Large Multi-modal Models","created":"2025-05-25","cited_by_count":1,"area":"mllm"},{"id":"2506.12336","title":"Benchmarking the Trustworthiness in Multimodal LLMs for Video Understanding","created":"2025-06-14","cited_by_count":1,"area":"mllm"},{"id":"2601.06106","title":"Judge Model for Large-scale Multimodality Benchmarks","created":"2026-01-03","cited_by_count":1,"area":null},{"id":"2603.06561","title":"EgoReasoner: Learning Egocentric 4D Reasoning via Task-Adaptive Structured Thinking","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2605.15342","title":"Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding","created":"2026-05-14","cited_by_count":1,"area":"lr"},{"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":"2606.03920","title":"Benchmarking Visual State Tracking in Multimodal Video Understanding","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.15320","title":"Conditional Multi-Event Temporal Grounding in Long-Form Video","created":"2026-06-13","cited_by_count":1,"area":"mllm"},{"id":"2510.06512","title":"LogSTOP: Temporal Scores over Prediction Sequences for Matching and Retrieval","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2603.15467","title":"Evaluating Time Awareness and Cross-modal Active Perception of Large Models via 4D Escape Room Task","created":"2026-03-16","cited_by_count":0,"area":"mllm"},{"id":"2604.10385","title":"GTASA: Ground Truth Annotations for Spatiotemporal Analysis, Evaluation and Training of Video Models","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2604.11627","title":"POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2604.17375","title":"When Text Hijacks Vision: Benchmarking and Mitigating Text Overlay-Induced Hallucination in Vision Language Models","created":"2026-04-19","cited_by_count":0,"area":"mllm"},{"id":"2605.23045","title":"The TIME Machine: On The Power of Motion for Efficient Perception","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.30673","title":"TeachObs: A Human-Validated Benchmark for Multimodal Teaching Observation and Model Evaluation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.16334","title":"Chronological Blindness: Benchmarking Temporal Reasoning in Vision-Language Models with CHRONOSIGHT","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2606.17627","title":"Divide, Deliberate, Decide: A Multi-Agent Framework for Fine-Grained Egocentric Action Recognition","created":"2026-06-16","cited_by_count":0,"area":"mllm"},{"id":"2606.18586","title":"APT: Atomic Physical Transitions for Causal Video-Language Understanding","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.22870","title":"VideoLatent: Video-Language Learning via Latent Self-Forcing","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2606.28593","title":"Animation2Code: Evaluating Temporal Visual Reasoning in Video-to-Code Generation","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2607.23962","title":"Development of Vision-Language Model-based GNSS Spoofing Detection for Autonomous Vehicle Navigation","created":"2026-07-27","cited_by_count":0,"area":"driving"},{"id":"2608.10764","title":"FADE: From Passive Verification to Active Discovery in Counterfactual Video Understanding","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.24763","title":"MoTE: Mixture of Task Experts for Multi-Task Video Understanding","created":"2026-08-25","cited_by_count":0,"area":"moe"},{"id":"2608.28666","title":"Improving Spatial-Temporal Reasoning in Video-Language Models with Structured Video Prompting","created":"2026-08-23","cited_by_count":0,"area":"lr"},{"id":"2609.00505","title":"ViTAL-X: Video-Text Alignment with Cross-Modal Temporal Edits","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.01515","title":"TempCloze: Can Video-LLMs Identify the Missing Middle?","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2609.05596","title":"Time-Aware Assistive Navigation","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.17112","title":"Not Another Text Benchmark: Putting the \"Visual\" Back in Visual Question Answering for Large Video Models","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.27493","title":"Information Capacity of Generative Video Compression: Quantifying the Rate-Compute Exchange at Identical Quality","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.30952","title":"MVVBench: Benchmarking 4D Reasoning in Vision-Language Models","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2610.12417","title":"WOVEN: Weaving Visual World Modeling into Multimodal LLMs","created":"2026-10-08","cited_by_count":0,"area":"wm"},{"id":"2610.12458","title":"OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning","created":"2026-10-08","cited_by_count":0,"area":"lr"},{"id":"2610.17234","title":"IsoVRBench: Video Reward Modeling Without Human Feedback","created":"2026-10-12","cited_by_count":0,"area":"alignment"}],"next_cursor":null}