{"total":120,"rows":[{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680,"area":null},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583,"area":"mllm"},{"id":"2406.16852","title":"Long Context Transfer from Language to Vision","created":"2024-06-24","cited_by_count":515,"area":"mllm"},{"id":"2303.11897","title":"TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering","created":"2023-03-21","cited_by_count":428,"area":null},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314,"area":"lr"},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243,"area":"mllm"},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213,"area":null},{"id":"2406.14515","title":"MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding","created":"2024-06-20","cited_by_count":182,"area":"mllm"},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2404.01258","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward","created":"2024-04-01","cited_by_count":147,"area":"mllm"},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84,"area":null},{"id":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74,"area":"lr"},{"id":"2205.01089","title":"ComPhy: Compositional Physical Reasoning of Objects and Events from Videos","created":"2022-05-02","cited_by_count":63,"area":null},{"id":"2203.13049","title":"Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning","created":"2022-03-24","cited_by_count":59,"area":null},{"id":"2501.08282","title":"LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding","created":"2025-01-14","cited_by_count":59,"area":"mllm"},{"id":"2212.09522","title":"MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering","created":"2022-12-19","cited_by_count":55,"area":null},{"id":"2305.03689","title":"COLA: A Benchmark for Compositional Text-to-image Retrieval","created":"2023-05-05","cited_by_count":53,"area":"mllm"},{"id":"2301.02074","title":"Test of Time: Instilling Video-Language Models with a Sense of Time","created":"2023-01-05","cited_by_count":51,"area":null},{"id":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40,"area":"lr"},{"id":"2311.14906","title":"AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering","created":"2023-11-25","cited_by_count":40,"area":"mllm"},{"id":"2406.09367","title":"Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs","created":"2024-06-13","cited_by_count":37,"area":"mllm"},{"id":"2412.01694","title":"Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation","created":"2024-12-02","cited_by_count":37,"area":"lr"},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35,"area":null},{"id":"2407.06189","title":"Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision","created":"2024-07-08","cited_by_count":25,"area":"mllm"},{"id":"2412.09582","title":"Neptune: The Long Orbit to Benchmarking Long Video Understanding","created":"2024-12-12","cited_by_count":25,"area":null},{"id":"2204.12037","title":"Causal Reasoning Meets Visual Representation Learning: A Prospective Study","created":"2022-04-26","cited_by_count":24,"area":"lr"},{"id":"2506.05332","title":"Unleashing Hour-Scale Video Training for Long Video-Language Understanding","created":"2025-06-05","cited_by_count":23,"area":"mllm"},{"id":"2409.17958","title":"The Hard Positive Truth about Vision-Language Compositionality","created":"2024-09-26","cited_by_count":22,"area":"mllm"},{"id":"2511.16668","title":"V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models","created":"2025-11-20","cited_by_count":22,"area":"lr"},{"id":"2406.14129","title":"Towards Event-oriented Long Video Understanding","created":"2024-06-20","cited_by_count":21,"area":"mllm"},{"id":"2408.00754","title":"Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model","created":"2024-08-01","cited_by_count":21,"area":"lr"},{"id":"2412.07012","title":"ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models","created":"2024-12-09","cited_by_count":21,"area":"mllm"},{"id":"2112.05892","title":"COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality","created":"2021-12-11","cited_by_count":19,"area":null},{"id":"2210.02081","title":"Locate before Answering: Answer Guided Question Localization for Video Question Answering","created":"2022-10-05","cited_by_count":19,"area":null},{"id":"2301.09071","title":"Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding","created":"2023-01-22","cited_by_count":19,"area":null},{"id":"2403.08755","title":"DAM: Dynamic Adapter Merging for Continual Video QA Learning","created":"2024-03-13","cited_by_count":19,"area":null},{"id":"2407.08101","title":"What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction","created":"2024-07-11","cited_by_count":18,"area":"mllm"},{"id":"2411.13281","title":"VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation","created":"2024-11-20","cited_by_count":18,"area":"mllm"},{"id":"2404.02145","title":"Iterated Learning Improves Compositionality in Large Vision-Language Models","created":"2024-04-02","cited_by_count":17,"area":"mllm"},{"id":"2603.20185","title":"VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking","created":"2026-03-20","cited_by_count":17,"area":"agents"},{"id":"2304.08682","title":"Learning Situation Hyper-Graphs for Video Question Answering","created":"2023-04-18","cited_by_count":16,"area":null},{"id":"2405.03272","title":"WorldQA: Multimodal World Knowledge in Videos through Long-Chain Reasoning","created":"2024-05-06","cited_by_count":16,"area":"wm"},{"id":"2204.07190","title":"Measuring Compositional Consistency for Video Question Answering","created":"2022-04-14","cited_by_count":15,"area":null},{"id":"2305.02519","title":"ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos","created":"2023-05-04","cited_by_count":15,"area":null},{"id":"2402.16050","title":"Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge","created":"2024-02-25","cited_by_count":14,"area":"mllm"},{"id":"2211.03779","title":"CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering","created":"2022-11-07","cited_by_count":13,"area":null},{"id":"2404.01299","title":"CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes","created":"2024-04-01","cited_by_count":13,"area":"lr"},{"id":"2406.10221","title":"Long Story Short: Story-level Video Understanding from 20K Short Films","created":"2024-06-14","cited_by_count":12,"area":"mllm"},{"id":"2408.02687","title":"Compositional Physical Reasoning of Objects and Events from Videos","created":"2024-08-02","cited_by_count":12,"area":null},{"id":"2506.07016","title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","created":"2025-06-08","cited_by_count":12,"area":"mllm"},{"id":"2304.08809","title":"SViTT: Temporal Learning of Sparse Video-Text Transformers","created":"2023-04-18","cited_by_count":11,"area":null},{"id":"2310.03635","title":"CLEVRER-Humans: Describing Physical and Causal Events the Human Way","created":"2023-10-05","cited_by_count":11,"area":null},{"id":"2412.02071","title":"Progress-Aware Video Frame Captioning","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2509.08502","title":"Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening","created":"2025-09-10","cited_by_count":11,"area":null},{"id":"2204.06105","title":"AGQA 2.0: An Updated Benchmark for Compositional Spatio-Temporal Reasoning","created":"2022-04-12","cited_by_count":10,"area":"lr"},{"id":"2406.10889","title":"VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment","created":"2024-06-16","cited_by_count":10,"area":"lr"},{"id":"2406.09646","title":"A Survey of Video Datasets for Grounded Event Understanding","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2407.03008","title":"Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering","created":"2024-07-03","cited_by_count":9,"area":"lr"},{"id":"2501.07214","title":"TimeLogic: A Temporal Logic Benchmark for Video QA","created":"2025-01-13","cited_by_count":9,"area":null},{"id":"2401.01529","title":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering","created":"2024-01-03","cited_by_count":8,"area":null},{"id":"2405.19723","title":"Encoding and Controlling Global Semantics for Long-form Video Question Answering","created":"2024-05-30","cited_by_count":8,"area":null},{"id":"2605.27589","title":"What-If World: A Causal Benchmark for General World Models in Embodied Scenarios","created":"2026-05-26","cited_by_count":8,"area":"wm"},{"id":"2310.02777","title":"The Role of Linguistic Priors in Measuring Compositional Generalization of Vision-Language Models","created":"2023-10-04","cited_by_count":6,"area":"mllm"},{"id":"2311.00556","title":"ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab","created":"2023-11-01","cited_by_count":6,"area":null},{"id":"2311.09064","title":"Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models","created":"2023-11-15","cited_by_count":6,"area":"wm"},{"id":"2404.04007","title":"Neural-Symbolic VideoQA: Learning Compositional Spatio-Temporal Reasoning for Real-world Video Question Answering","created":"2024-04-05","cited_by_count":6,"area":"lr"},{"id":"2506.07643","title":"Synthetic Visual Genome","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2404.00973","title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2506.08227","title":"A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks","created":"2025-06-09","cited_by_count":5,"area":null},{"id":"2512.05513","title":"Know-Show: Benchmarking Video-Language Models on Spatio-Temporal Grounded Reasoning","created":"2025-12-05","cited_by_count":5,"area":"lr"},{"id":"2302.02136","title":"Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer","created":"2023-02-04","cited_by_count":4,"area":null},{"id":"2306.16533","title":"ICSVR: Investigating Compositional and Syntactic Understanding in Video Retrieval Models","created":"2023-06-28","cited_by_count":4,"area":null},{"id":"2410.22829","title":"Situational Scene Graph for Structured Human-centric Situation Understanding","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2504.05925","title":"SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2505.03581","title":"DyGEnc: Encoding a Sequence of Textual Scene Graphs to Reason and Answer Questions in Dynamic Scenes","created":"2025-05-06","cited_by_count":4,"area":"lr"},{"id":"2512.14870","title":"HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2401.17343","title":"YTCommentQA: Video Question Answerability in Instructional Videos","created":"2024-01-30","cited_by_count":3,"area":null},{"id":"2407.05118","title":"SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding","created":"2024-07-06","cited_by_count":3,"area":null},{"id":"2412.08221","title":"Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation Training","created":"2024-12-11","cited_by_count":3,"area":"diffusion"},{"id":"2505.13429","title":"Understanding Complexity in VideoQA via Visual Program Generation","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2602.23543","title":"Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2210.03941","title":"Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling","created":"2022-10-08","cited_by_count":2,"area":null},{"id":"2210.10300","title":"Dense but Efficient VideoQA for Intricate Compositional Reasoning","created":"2022-10-19","cited_by_count":2,"area":"lr"},{"id":"2304.02313","title":"Personality-aware Human-centric Multimodal Reasoning: A New Task, Dataset and Baselines","created":"2023-04-05","cited_by_count":2,"area":"lr"},{"id":"2412.19304","title":"Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries","created":"2024-12-26","cited_by_count":2,"area":"lr"},{"id":"2509.14227","title":"Cin\\'{e}aste: A Fine-grained Contextual Movie Question Answering Benchmark","created":"2025-09-17","cited_by_count":2,"area":"mllm"},{"id":"2512.11336","title":"UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models","created":"2025-12-12","cited_by_count":2,"area":"mllm"},{"id":"2604.01460","title":"Reinforcing Consistency in Video MLLMs with Structured Rewards","created":"2026-04-01","cited_by_count":2,"area":"mllm"},{"id":"2604.20136","title":"IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2605.23176","title":"DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving","created":"2026-05-22","cited_by_count":2,"area":"driving"},{"id":"2401.17773","title":"SNP-S3: Shared Network Pre-training and Significant Semantic Strengthening for Various Video-Text Tasks","created":"2024-01-31","cited_by_count":1,"area":null},{"id":"2505.05318","title":"Mapping User Trust in Vision Language Models: Research Landscape, Challenges, and Prospects","created":"2025-05-08","cited_by_count":1,"area":"mllm"},{"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":"2507.14743","title":"InterAct-Video: Reasoning-Rich Video QA for Urban Traffic","created":"2025-07-19","cited_by_count":1,"area":null},{"id":"2508.11163","title":"MobQA: A Benchmark Dataset for Semantic Understanding of Human Mobility Data through Question Answering","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2509.05368","title":"Long-Horizon Visual Imitation Learning via Plan and Code Reflection","created":"2025-09-04","cited_by_count":1,"area":"offlinerl"},{"id":"2509.24445","title":"Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2512.06673","title":"Detector-Empowered Video Large Language Model for Efficient Spatio-Temporal Grounding","created":"2025-12-07","cited_by_count":1,"area":"mllm"},{"id":"2603.21559","title":"Revisiting Weakly-Supervised Video Scene Graph Generation via Pair Affinity Learning","created":"2026-03-23","cited_by_count":1,"area":null}],"next_cursor":"100"}