{"total":33,"rows":[{"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":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243,"area":"mllm"},{"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":"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":"2305.03689","title":"COLA: A Benchmark for Compositional Text-to-image Retrieval","created":"2023-05-05","cited_by_count":53,"area":"mllm"},{"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":"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":"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":"2406.14129","title":"Towards Event-oriented Long Video Understanding","created":"2024-06-20","cited_by_count":21,"area":"mllm"},{"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":"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":"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":"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":"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":"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":"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":"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":"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":"2606.09142","title":"Decoding Pedestrian Crossing Intention from Egocentric Vision via Vision Language Models","created":"2026-06-08","cited_by_count":1,"area":"mllm"},{"id":"2606.15320","title":"Conditional Multi-Event Temporal Grounding in Long-Form Video","created":"2026-06-13","cited_by_count":1,"area":"mllm"},{"id":"2503.15846","title":"A Closer Look at Dynamic Scene Graph Generation In the Era of Multimodal Large Language Models","created":"2025-03-20","cited_by_count":0,"area":"mllm"},{"id":"2511.13458","title":"Trust in Vision-Language Models: Insights from a Participatory User Workshop","created":"2025-11-17","cited_by_count":0,"area":"mllm"},{"id":"2603.14953","title":"Learning Question-Aware Keyframe Selection with Synthetic Supervision for Video Question Answering","created":"2026-03-16","cited_by_count":0,"area":"mllm"}],"next_cursor":null}