{"list":"other","total":72,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2401.10020","title":"Self-Rewarding Language Models","created":"2024-01-18","cited_by_count":681},{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2406.16852","title":"Long Context Transfer from Language to Vision","created":"2024-06-24","cited_by_count":515},{"id":"2312.00849","title":"RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback","created":"2023-12-01","cited_by_count":412},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2402.01306","title":"KTO: Model Alignment as Prospect Theoretic Optimization","created":"2024-02-02","cited_by_count":264},{"id":"2501.13826","title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","created":"2025-01-23","cited_by_count":236},{"id":"2403.11481","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","created":"2024-03-18","cited_by_count":229},{"id":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","cited_by_count":229},{"id":"2409.14485","title":"Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding","created":"2024-09-22","cited_by_count":213},{"id":"2501.12386","title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","created":"2025-01-21","cited_by_count":211},{"id":"2007.10937","title":"MovieNet: A Holistic Dataset for Movie Understanding","created":"2020-07-21","cited_by_count":206},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178},{"id":"2502.21271","title":"Adaptive Keyframe Sampling for Long Video Understanding","created":"2025-02-28","cited_by_count":167},{"id":"2502.04326","title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","created":"2025-02-06","cited_by_count":155},{"id":"2501.12380","title":"MMVU: Measuring Expert-Level Multi-Discipline Video Understanding","created":"2025-01-21","cited_by_count":137},{"id":"2404.03413","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","created":"2024-04-04","cited_by_count":118},{"id":"2505.18079","title":"Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding","created":"2025-05-23","cited_by_count":98},{"id":"2410.03226","title":"Frame-Voyager: Learning to Query Frames for Video Large Language Models","created":"2024-10-04","cited_by_count":83},{"id":"2506.23825","title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams","created":"2025-06-30","cited_by_count":81},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65},{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61},{"id":"2412.10471","title":"VCA: Video Curious Agent for Long Video Understanding","created":"2024-12-12","cited_by_count":56},{"id":"2407.03104","title":"KeyVideoLLM: Towards Large-scale Video Keyframe Selection","created":"2024-07-03","cited_by_count":54},{"id":"2303.17839","title":"Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations","created":"2023-03-31","cited_by_count":46},{"id":"2407.12679","title":"Goldfish: Vision-Language Understanding of Arbitrarily Long Videos","created":"2024-07-17","cited_by_count":40},{"id":"2105.04066","title":"Reconstructive Sequence-Graph Network for Video Summarization","created":"2021-05-10","cited_by_count":34},{"id":"2310.04900","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","created":"2023-10-07","cited_by_count":34},{"id":"2406.16620","title":"OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer","created":"2024-06-24","cited_by_count":34},{"id":"2504.10068","title":"Mavors: Multi-granularity Video Representation for Multimodal Large Language Model","created":"2025-04-14","cited_by_count":32},{"id":"1904.06400","title":"Distributed Deep Learning Model for Intelligent Video Surveillance Systems with Edge Computing","created":"2019-04-12","cited_by_count":28},{"id":"2502.06428","title":"CoS: Chain-of-Shot Prompting for Long Video Understanding","created":"2025-02-10","cited_by_count":27},{"id":"2404.01476","title":"TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering","created":"2024-04-01","cited_by_count":25},{"id":"2508.04369","title":"TSPO: Temporal Sampling Policy Optimization for Long-form Video Language Understanding","created":"2025-08-06","cited_by_count":25},{"id":"2506.05332","title":"Unleashing Hour-Scale Video Training for Long Video-Language Understanding","created":"2025-06-05","cited_by_count":23},{"id":"2303.15879","title":"STMixer: A One-Stage Sparse Action Detector","created":"2023-03-28","cited_by_count":22},{"id":"2503.08585","title":"HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding","created":"2025-03-11","cited_by_count":17},{"id":"2503.13016","title":"Efficient Motion-Aware Video MLLM","created":"2025-03-17","cited_by_count":14},{"id":"2510.08559","title":"SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models","created":"2025-10-09","cited_by_count":13},{"id":"2403.14174","title":"Unified Static and Dynamic Network: Efficient Temporal Filtering for Video Grounding","created":"2024-03-21","cited_by_count":12},{"id":"2312.04931","title":"Long Video Understanding with Learnable Retrieval in Video-Language Models","created":"2023-12-08","cited_by_count":9},{"id":"2412.11228","title":"Uni-AdaFocus: Spatial-temporal Dynamic Computation for Video Recognition","created":"2024-12-15","cited_by_count":9},{"id":"2505.23922","title":"ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding","created":"2025-05-29","cited_by_count":8},{"id":"2507.02626","title":"VRAgent-R1: Boosting Video Recommendation with MLLM-based Agents via Reinforcement Learning","created":"2025-07-03","cited_by_count":8},{"id":"2602.07801","title":"VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos","created":"2026-02-08","cited_by_count":7},{"id":"2602.22932","title":"MSJoE: Jointly Evolving MLLM and Sampler for Efficient Long-Form Video Understanding","created":"2026-02-26","cited_by_count":6},{"id":"2604.14149","title":"One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding","created":"2026-04-15","cited_by_count":5},{"id":"2606.02522","title":"Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events","created":"2026-06-01","cited_by_count":5},{"id":"2511.17945","title":"Test-Time Temporal Sampling for Efficient MLLM Video Understanding","created":"2025-11-22","cited_by_count":3},{"id":"2510.09266","title":"CFVBench: A Comprehensive Video Benchmark for Fine-grained Multimodal Retrieval-Augmented Generation","created":"2025-10-10","cited_by_count":2}],"next_cursor":null}