The DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.
MLVU: Benchmarking Multi-task Long Video Understanding
Open accessAbstract
The evaluation of Long Video Understanding (LVU) performance poses an important but challenging research problem. Despite previous efforts, the existing video understanding benchmarks are severely constrained by several issues, especially the insufficient lengths of videos, a lack of diversity in video types and evaluation tasks, and the inappropriateness for evaluating LVU performances. To address the above problems, we propose a new benchmark called MLVU (Multitask Long Video Understanding Benchmark) for the comprehensive and in-depth evaluation of LVU. MLVU presents the following critical values: 1) The substantial and flexible extension of video lengths, which enables the benchmark to evaluate LVU performance across a wide range of durations. 2) The inclusion of various video genres, such as movies, surveillance, egocentric videos, and cartoons, reflects the models’ LVU performances in different scenarios. 3) The development of diversified evaluation tasks, which enables a comprehensive examination of MLLMs’ key abilities in long-video understanding. The empirical study with 23 latest MLLMs reveals significant room for improvement in today’s technique, as all existing methods struggle with most of the evaluation tasks and exhibit severe performance degradation when handling longer videos. Additionally, it suggests that factors such as context length, image-understanding ability, and the choice of LLM backbone can play critical roles in future advancements. We anticipate that MLVU will advance the research of LVU by providing a comprehensive and in-depth analysis of MLLMs. The code and dataset can be accessed from https://github.com/JUNJIE99/MLVU.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Most existing LVQA benchmarks mainly focus on visual understanding, leaving a gap in evaluating higher-level cognitive abilities that rely on long-term memory, such as understanding persons, extracting general knowledge, and performing cross-modal reasoning.
“Most existing LVQA benchmarks [2, 11, 50, 62] mainly focus on visual understanding, such as action recognition and spatial/temporal perception, leaving a gap in evaluating higher-level cognitive abilities that rely on long-term memory and are crucial for real-world agents, such as understanding persons, extracting general knowledge, and performing cross-modal reasoning.”
From Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory (2025) · cites this paper as [62]
Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 8
- [6][6] Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877-1901, 2020. 1 -
- [15][15] Kristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang, Miao Liu, Xingyu Liu, et al. Ego4d: Around the world in 3,000 hours of egocentric video. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 18995-19012, 2022. 1, 3, 4 -
- [34][34] Karttikeya Mangalam, Raiymbek Akshulakov, and Jitendra Malik. Egoschema: A diagnostic benchmark for very longform video language understanding. Advances in Neural Information Processing Systems, 36, 2023. 1, 2, 3 -
- [48][48] Bo Wu, Shoubin Yu, Zhenfang Chen, Joshua B Tenenbaum, and Chuang Gan. Star: A benchmark for situated reasoning in real-world videos. In Thirty-fifth conference on neural information processing systems datasets and benchmarks track (Round 2), 2021. 3 -
- [52][52] Jun Xu, Tao Mei, Ting Yao, and Yong Rui. Msr-vtt: A large video description dataset for bridging video and language. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5288-5296, 2016. 1, 2, 3 -
- [55][55] Kexin Yi, Chuang Gan, Yunzhu Li, Pushmeet Kohli, Jiajun Wu, Antonio Torralba, and Joshua B Tenenbaum. Clevrer: Collision events for video representation and reasoning. In International Conference on Learning Representations, 2019. 4 -
- [56][56] Zhou Yu, Dejing Xu, Jun Yu, Ting Yu, Zhou Zhao, Yueting Zhuang, and Dacheng Tao. Activitynet-qa: A dataset for understanding complex web videos via question answering. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 9127-9134, 2019. 3 -
- [63][63] Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. Minigpt-4: Enhancing visionlanguage understanding with advanced large language models. In The Twelfth International Conference on Learning Representations, 2023. 2
Cited by
Sorted by citations
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal ModelsPreprint
Zhu, J., Wang, W., Chen, Z., Liu, Z., Ye, S., Gu, L., Tian, H., Duan, Y., Su, W., Shao, J., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.10479 · Cited by 2,109
Self-citationInternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and EfficiencyPreprint
Wang, W., Gao, Z., Gu, L., Pu, H., Cui, L., Wei, X., Liu, Z., Jing, L., Ye, S., Shao, J., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.18265 · Cited by 1,803
Self-citationChen, Z., Wang, W., Cao, Y. Q., Liu, Y., Gao, Z., Cui, E., Zhu, J., Ye, S., Tian, H., Liu, Z., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.05271 · Cited by 1,785
Self-citationLLaVA-Video: Video Instruction Tuning With Synthetic DataPreprint
Zhang, Y., Wu, J., Li, W., Li, B., Ma, Z., Liu, Z., & Li, C. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.02713 · Cited by 857
Self-citationVideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMsPreprint
Cheng, Z., Leng, S., Zhang, H., Xin, Y., Li, X., Chen, G., Zhu, Y., Zhang, W., Luo, Z., Zhao, D., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2406.07476 · Cited by 832
Kimi-VL Technical ReportPreprint
Kimi Team, Du, A., Yin, B., Xing, B., Qu, B., Wang, B., Chen, C., Zhang, C., Du, C., Wei, C., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.07491 · Cited by 517
Seed1.5-VL Technical ReportPreprint
Guo, D., Wu, F., Zhu, F., Leng, F., Shi, G., Chen, H., Fan, H., Wang, J., Jiang, J., Wang, J., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.07062 · Cited by 479
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language UnderstandingPreprint
Shen, X., Xiong, Y., Zhao, C., Wu, L., Chen, J., Zhu, C., Liu, Z., Xiao, F., Varadarajan, B., Bordes, F., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.17434 · Cited by 308
Self-citationInternVideo2.5: Empowering Video MLLMs with Long and Rich Context ModelingPreprint
Wang, Y., Li, X., Yan, Z., He, Y., Yu, J., Zeng, X., Wang, C., Ma, C., Huang, H. K., Gao, J., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.12386 · Cited by 240
Unified Reward Model for Multimodal Understanding and GenerationPreprint
Wang, Y., Zang, Y., Li, H., Jin, C., & Wang, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.05236 · Cited by 225
Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional VideosPreprint
Hu, K., Wu, P., Pu, F., Wang, X., Zhang, Y., Yue, X., Li, B., & Liu, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.13826 · Cited by 224
Self-citationZhang, P., Dong, X., Zang, Y., Cao, Y., Qian, R., Chen, L., Guo, Q., Duan, H., Wang, B., Ouyang, L., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.03320 · Cited by 218
VideoChat-Flash: Hierarchical Compression for Long-Context Video ModelingPreprint
Li, X., Wang, Y., Yu, J., Zeng, X., Zhu, Y., Huang, H. K., Gao, J., Li, K., He, Y., Wang, C., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.00574 · Cited by 213
LLaDA-V: Large Language Diffusion Models with Visual Instruction TuningPreprint
You, Z., Nie, S., Zhang, X., Hu, J., Zhou, J., Lu, Z., Wen, J.-R., & Li, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.16933 · Cited by 174
Self-citationA Comprehensive Survey on Long Context Language ModelingPreprint
Liu, J., Zhu, D., Bai, Z., He, Y., Liao, H., Que, H., Wang, Z., Zhang, C., Zhang, G., Zhang, J., et al. (2025) · arXiv (Cornell University) · doi:10.13140/rg.2.2.22279.51369 · Cited by 174
Self-citationOryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary ResolutionPreprint
Liu, Z., Dong, Y., Liu, Z., Hu, W., Lu, J., & Rao, Y. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.12961 · Cited by 137
Self-citationVideo-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension
Luo, Y., Zheng, X., Li, G., Yin, S., Lin, H., Fu, C., Huang, J., Ji, J., Chao, F., Luo, J., et al. (2025) · neural information processing systems · doi:10.52202/085713-5602 · Cited by 134
A Survey on Large Language Model Acceleration based on KV Cache ManagementPreprint
Li, H., Li, Y., Tian, A., Tang, T., Xu, Z., Chen, X., Hu, N., Dong, W., Li, Q., & Chen, L. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.19442 · Cited by 134
Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input
Liu, J., Wang, Y., Ma, H., Wu, X., Ma, X., Wei, X., Jiao, J., Wu, E., & Hu, J. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-025-02620-2 · Cited by 132
WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMsPreprint
Hong, J., Yan, S., Cai, J., Jiang, X., Hu, Y., & Xie, W. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.04326 · Cited by 131
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision TokenPreprint
Zhang, S., Fang, Q., Yang, Z., & Feng, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.03895 · Cited by 122
video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language ModelsPreprint
Tang, C., Li, Y., Yang, Y., Zhuang, J., Sun, G., Li, W., Ma, Z., & Zhang, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.15220 · Cited by 102
A Survey of Multimodal Retrieval-Augmented GenerationPreprint
Mei, L., Mo, S., Yang, Z., & Chen, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.08748 · Cited by 101
Bai, S., Chen, K., Liu, X., Wang, J., Ge, W., Song, S., Dang, K., Wang, P., Wang, S., Tang, J., et al. (2025) · arXiv · doi:10.48550/arxiv.2502.13923 · Cited by 94
Fei, J., Li, D., Deng, Z., Wang, Z., Liu, G., & Wang, H. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.14023 · Cited by 92
VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos
Ren, X., Xu, L., Xia, L., Wang, S., Yin, D., & Huang, C. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770854.3783944 · Cited by 90
MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMsPreprint
Fu, C., Zhang, Y., Yin, S., Li, B. H., Fang, X., Zhao, S., Duan, H., Sun, X. L., Liu, Z., Wang, L., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.15296 · Cited by 90
Self-citationPerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
Cho, J. H., Madotto, A., Mavroudi, E., Afouras, T., Nagarajan, T., Maaz, M., Song, Y., Ma, T., Hu, S., Jain, S. D., et al. (2025) · neural information processing systems · doi:10.52202/085713-0795 · Cited by 87
EgoLife: Towards Egocentric Life Assistant
Yang, J., Liu, S., Guo, H., Dong, Y., Zhang, X., Zhang, S., Wang, P., Zhou, Z., Xie, B., Wang, Z., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02690 · Cited by 85
Self-citationOVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?
Niu, J., Li, Y., Miao, Z., Ge, C., Zhou, Y., He, Q., Dong, X., Duan, H., Ding, S., Qian, R., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01761 · Cited by 83
Kwai Keye-VL Technical ReportPreprint
Kwai Keye Team, Yang, B., Wen, B., Liu, C., Chu, C., Song, C., Rao, C., Yi, C., Li, D., Zang, D., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.01949 · Cited by 81
Chen, S., Lan, X., Yuan, Y., Jie, Z., & Ma, L. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.18211 · Cited by 78
Apollo: An Exploration of Video Understanding in Large Multimodal Models
Zohar, O., Wang, X., Dubois, Y., Mehta, N., Xiao, T., Hansen-Estruch, P., Yu, L., Wang, X., Juefei-Xu, F., Zhang, N., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01760 · Cited by 75
Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
Zhang, Q., Liu, M., Li, L., Lu, M., Zhang, Y., Pan, J., She, Q., & Zhang, S. (2025) · neural information processing systems · doi:10.52202/085713-0855 · Cited by 71
Streaming Video Question-Answering with In-context Video KV-Cache RetrievalPreprint
Di, S., Yu, Z., Zhang, G., Li, H., Zhong, T., Cheng, H., Li, B., He, W., Shu, F., & Jiang, H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.00540 · Cited by 66
CG-Bench: Clue-grounded Question Answering Benchmark for Long Video UnderstandingPreprint
Chen, G., Liu, Y., Huang, Y., He, Y., Pei, B., Xu, J., Wang, L., Lü, T., & Wang, L. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.12075 · Cited by 65
V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal ReasoningPreprint
Cheng, Z., Hu, J., Liu, Z., Si, C., Li, W., & Gong, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.11495 · Cited by 65
Self-citationVideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video ReasoningPreprint
Liu, Y., Lin, K. Q., Chen, C. W., & Shou, M. Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.13444 · Cited by 65
LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval
Ning, Z., Liu, G., Jin, Q., Li, C., Ding, W., Guo, M., & Zhao, J. (2026) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1145/3770743.3804012 · Cited by 63
TinyLLaVA-Video-R1: Towards Smaller LMMs for Video ReasoningPreprint
Zhang, X., Wen, S., Wu, W., & Huang, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.09641 · Cited by 61
Frame-Voyager: Learning to Query Frames for Video Large Language ModelsPreprint
Yu, S., Jin, C., Wang, H., Chen, Z., Jin, S., Zuo, Z., Xu, X., Sun, Z., Zhang, B., Wu, J., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.03226 · Cited by 60
Self-citationEagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language ModelsPreprint
Chen, G., Li, Z., Wang, S., Jiang, J., Liu, Y., Lü, L., Huang, D.-A., Byeon, W., Le, M., Rintamaki, T., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.15271 · Cited by 58
VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception
Yan, Z., He, Y., Li, X., Yue, Z., Zeng, X., Wang, L., Yu, Q., Wang, L., & Wang, Z. (2025) · neural information processing systems · doi:10.52202/085713-3976 · Cited by 57
Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA
Park, J., Ranasinghe, K., Kahatapitiya, K., Ryu, W., Kim, D., & Ryoo, M. S. (2026) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2026.eacl-long.164 · Cited by 56
LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents
Chen, B., Yue, Z., Chen, S., Wang, Z., Liu, Y., Li, P., & Wang, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01882 · Cited by 55
Zhang, P., Dong, X., Cao, Y., Zang, Y., Qian, R., Wei, X., Chen, L., Li, Y., Niu, J., Ding, S., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.09596 · Cited by 55
Q-Frame: Query-Aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs
Zhang, S., Yang, J., Yin, J., Luo, Z., Luan, J., & Plus, M. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02048 · Cited by 54
Streaming Video Understanding and Multi-round Interaction with Memory-enhanced KnowledgePreprint
Xiong, H., Yang, Z., Yu, J., Zhuge, Y., Zhang, P., Zhu, J., & Lu, H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.13468 · Cited by 54
ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding
Zhou, Y., He, Y., Su, Y., Han, S., Jang, J., Bertasius, G., Bansal, M., & Yao, H. (2025) · neural information processing systems · doi:10.52202/085713-5066 · Cited by 53
Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video UnderstandingPreprint
Liu, X., Shu, Y., Liu, Z., Li, A., Tian, Y., & Zhao, B. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.18478 · Cited by 53
Self-citationStreamForest: Efficient Online Video Understanding with Persistent Event Memory
Zeng, X., Qiu, K., Zhang, Q., Li, X., Wang, J., Li, J., Yan, Z., Tian, K., Tian, M., Zhao, X., et al. (2025) · neural information processing systems · doi:10.52202/085713-2547 · Cited by 51
Towards Anticipatory Agents for Streaming Video Understanding
Yang, H., Tang, F., Zhao, L., Zhuang, X., Lu, Y., An, X., Hu, M., Zhang, X., Swikir, A., He, J., et al. (2026) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/2026.findings-emnlp.65 · Cited by 49
ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video UnderstandingPreprint
Wang, X., Si, Q., Wu, J., Zhu, S., Cao, L. J., & Nie, L. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.20504 · Cited by 48
VideoRoPE: What Makes for Good Video Rotary Position Embedding?Preprint
Wei, X., Liu, X., Zang, Y., Dong, X., Zhang, P., Cao, Y., Jian, T., Duan, H., Guo, Q., Wang, J., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.05173 · Cited by 48
EgoPlan-Bench2: A Benchmark for Multimodal Large Language Model Planning in Real-World Scenarios
Qiu, L., Chen, Y., Ge, Y., Ge, Y., Shan, Y., & Liu, X. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02826-y · Cited by 47
Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models
Liu, X., Wang, Y., Ma, J., & Zhang, L. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.98 · Cited by 47
VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought ReasoningPreprint
Qi, Y., Zhao, Y., Zeng, Y., Bao, X., Huang, W., Chen, L., Chen, Z., Zhao, J., Qi, Z., & Zhao, F. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.07956 · Cited by 47
Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV SparsificationPreprint
Qin, M., Liu, X., Liang, Z., Shu, Y., Yuan, H., Zhou, J., Xiao, S., Zhao, B., & Liu, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.19225 · Cited by 46
Self-citationTOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation ModelsPreprint
Shangguan, Z., Li, C., Ding, Y., Zheng, Y., Zhao, Y., Fitzgerald, T., & Cohan, A. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.23266 · Cited by 45
LLaVA-OneVision: Easy Visual Task Transfer
Li, B., Zhang, Y., Guo, D., Zhang, R., Li, F., Zhang, H., Zhang, K., Zhang, P., Li, Y., Liu, Z., et al. (2024) · arXiv · doi:10.48550/arxiv.2408.03326 · Cited by 44
Self-citationStreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant
Wang, H., Feng, B., Lai, Z., Xu, M., Li, S.-Y., Ge, W., Dehghan, A., Cao, M., & Huang, P. (2025) · neural information processing systems · doi:10.52202/085713-4406 · Cited by 43
VideoExplorer: Think With Videos For Agentic Long-Video UnderstandingPreprint
Yuan, H., Liu, Z., Zhou, J., Qian, H., Shu, Y., Sebe, N., Wen, J.-R., & Dou, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.10821 · Cited by 42
Self-citationFlash-Vstream: Efficient Real-Time Understanding for Long Video Streams
Zhang, H., Wang, Y., Tang, Y., Liu, Y., Feng, J., & Jin, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01957 · Cited by 41
VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language ModelsPreprint
Zhang, C., Ma, K., Fang, T., Yu, W., Zhang, H., Zhang, Z., Mi, H., & Yu, D. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.22654 · Cited by 41
VQA 2 : Visual Question Answering for Video Quality Assessment
Jia, Z., Zhang, Z., Qian, J., Wu, H., Sun, W., Li, C., Liu, X., Lin, W., Zhai, G., & Min, X. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754696 · Cited by 40
Online Video Understanding: OVBench and VideoChat-Online
Huang, Z., Li, X., Li, J., Wang, J., Zeng, X., Liang, C., Wu, T., Chen, X., Li, L., & Wang, L. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00316 · Cited by 37
BOLT: Boost Large Vision-Language Model Without Training for Long-Form Video Understanding
Liu, S., Zhao, C., Xu, T., & Ghanem, B. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00315 · Cited by 36
A Survey on Multimodal Benchmarks: In the Era of Large AI ModelsPreprint
Li, L., Chen, G., Shi, H., Xiao, J., & Chen, L. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.18142 · Cited by 36
Temporal Preference Optimization for Long-Form Video UnderstandingPreprint
Li, R., Wang, X., Zhang, Y., Zohar, O., Wang, Z., & Yeung, S. Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.13919 · Cited by 36
Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and GenerationPreprint
AI, I., :, Ma, B., Zou, C., Du, C., Yan, C., Jin, C., Shen, C., Lian, C., Fan, C., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.24821 · Cited by 36
Self-citationInfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding
Kim, M., Shim, K., Choi, J., & Chang, S. (2025) · neural information processing systems · doi:10.52202/085713-4639 · Cited by 35
Zou, H., Luo, T., Xie, G., Victor, Zhang, Lv, F., Wang, G., Chen, J., Wang, Z., Zhang, H., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.18938 · Cited by 35
StreamChat: Chatting with Streaming VideoPreprint
Liu, J., Yu, Z., Lan, S., Wang, S., Fang, R., Kautz, J., Li, H., & Alvare, J. M. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.08646 · Cited by 35
LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMsPreprint
Sun, B., Zhao, J., Wei, X., & Hou, Q. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.21862 · Cited by 35
Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMsPreprint
Zhao, Z., Lu, H., Huo, Y., Du, Y., Yue, T., Guo, L., Wang, B., Chen, W., & Liu, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2406.09367 · Cited by 34
AToken: A Unified Tokenizer for VisionPreprint
Lu, J., Song, L., Xu, M., Ahn, B., Wang, Y., Chen, C., Dehghan, A., & Yang, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.14476 · Cited by 34
VAMBA: Understanding Hour-Long Videos with Hybrid Mamba-Transformers
Ren, W., Ma, W., Yang, H., Wei, C., Zhang, G., & Chen, W. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01969 · Cited by 33
SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language ModelsPreprint
Xia, H., Yang, Z., Zou, J., Tracy, R., Wang, Y., Lu, C., Lai, C., He, Y., Shao, X., Xie, Z., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.08474 · Cited by 32
Benchmark Evaluations, Applications, and Challenges of Large Vision Language Models: A SurveyPreprint
Li, Z., Wu, X., Du, H., Nghiem, H. T., & Shi, G. (2025) · Qeios · doi:10.32388/gxr68q · Cited by 31
CoS: Chain-of-Shot Prompting for Long Video UnderstandingPreprint
Hu, J., Cheng, Z., Si, C., Li, W., & Gong, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.06428 · Cited by 31
Yan, S., Ren, B., Xiong, Z., Paudel, D. P., Gool, L. V., Demir, B., Sebe, N., & Rota, P. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.01667 · Cited by 31
NVIDIA Nemotron Nano V2 VLPreprint
NVIDIA, :, Deshmukh, A. S., Chumachenko, K., Rintamaki, T., Le, M., Poon, T., Taheri, D. M., Karmanov, I., Liu, G., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.03929 · Cited by 32
Accelerating Streaming Video Large Language Models via Hierarchical Token CompressionPreprint
Wang, Y., Liu, X., Gui, X., Lin, X., Yang, B., Liao, C., Chen, T., & Zhang, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.00891 · Cited by 31
VideoITG: Multimodal Video Understanding with Instructed Temporal GroundingPreprint
Wang, S., Chen, G., Huang, D.-A., Li, Z., Li, M., Li, G., Álvarez, J. M., Zhang, L., & Yu, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.13353 · Cited by 30
PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual TrainingPreprint
Chen, C., Liu, M., Jing, C., Zhou, Y., Rao, F., Chen, H., Zhang, B., & Shen, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.06486 · Cited by 29
Self-citationRe-thinking Temporal Search for Long-Form Video Understanding
Ye, J., Wang, Z., Sun, H., Chandrasegaran, K., Durante, Z., Eyzaguirre, C., Bisk, Y., Niebles, J. C., Adeli, E., Fei-Fei, L., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00802 · Cited by 28
Scaling Video-Language Models to 10K Frames via Hierarchical Differential DistillationPreprint
Cheng, C., Guan, J., Wu, W., & Yan, R. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.02438 · Cited by 28
STORM: Token-Efficient Long Video Understanding for Multimodal LLMsPreprint
Jiang, J., Li, X., Liu, Z., Li, M., Guo, C., Li, Z., Huang, D.-A., Liu, G., Yu, Z., Keutzer, K., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.04130 · Cited by 28
Self-citationBai, S., Cai, Y., Chen, R., Chen, K., Chen, X., Cheng, Z., Deng, L., Ding, W., Gao, C., Ge, C., et al. (2025) · arXiv · doi:10.48550/arxiv.2511.21631 · Cited by 27
Self-citationDynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM
Wang, H., Nie, Y., Ye, Y., Wang, Y., Shuai, L. I., Yu, H., Lu, J., & Huang, C. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01935 · Cited by 27
FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding
Tu, C., Zhang, L., Chen, P., Ye, P., Zeng, X., Cheng, W., Yu, G., & Chen, T. (2025) · neural information processing systems · doi:10.52202/085713-4791 · Cited by 27
Neptune: The Long Orbit to Benchmarking Long Video UnderstandingPreprint
Nagrani, A., Zhang, M., Mehran, R., Hornung, R., Gundavarapu, N. B., Jha, N., Myers, A., Zhou, X., Gong, B., Schmid, C., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.09582 · Cited by 27
FindingDory: A Benchmark to Evaluate Memory in Embodied Agents
Yadav, K., Ali, Y., Gupta, G., Gal, Y., & Kira, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37086-0_13 · Cited by 26
MR. Video: "MapReduce" is the Principle for Long Video UnderstandingPreprint
Pang, Z., & Wang, Y.-X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.16082 · Cited by 26
PAI-Bench: A Comprehensive Benchmark For Physical AIPreprint
Zhou, F., Huang, J., Li, J. J., Ramanan, D., & Shi, H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.01989 · Cited by 26
Xu, M., Gao, M., Li, S., Lu, J., Gan, Z., Lai, Z., Cao, M., Kang, K., Yang, Y., & Dehghan, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.18943 · Cited by 26
VideoLucy: Deep Memory Backtracking for Long Video Understanding
Zuo, J., Deng, Y., Kong, L., Yang, J., Jin, R., Zhang, Y., Sang, N., Pan, L., Liu, Z., & Gao, C. (2025) · neural information processing systems · doi:10.52202/085713-0864 · Cited by 25
Self-citationInfiniBench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and TV Shows
Ataallah, K., Bakr, E. M., Ahmed, M., Gou, C., Pahwa, K., Ding, J., & Elhoseiny, M. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.984 · Cited by 25
Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding
Shen, X., Zhang, W., Chen, J., & Elhoseiny, M. (2025) · neural information processing systems · doi:10.52202/085713-3372 · Cited by 25
FRAG: Frame Selection Augmented Generation for Long Video and Long Document UnderstandingPreprint
Huang, D.-A., Radhakrishnan, S., Yu, Z., & Kautz, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.17447 · Cited by 25
Metadata
- Authors
- Zhou, J., Shu, Y., Zhao, B., Wu, B., Liang, Z., Xiao, S., Qin, M., Yang, X., Xiong, Y., Zhang, B., Huang, T., & Liu, Z.
- Affiliations
- Beijing University of Posts and Telecommunications (CN)
- Beijing Academy of Artificial Intelligence (CN)
- Shanghai Jiao Tong University (CN)
- Zhejiang University (CN)
- ORCID
- Venue
- 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2025-06-10
- Pages
- 13691-13701
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4413144845
- Cited by
- 44
- References
- 0
- Citations by year
- 2026: 37 · 2025: 6
- FWCI
- 32.37
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-sa)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Analysis and Summarization
- Keywords
- long video understanding, benchmark, multi-task evaluation, multimodal large language models, video length, video genres, surveillance video, egocentric video, animated cartoons, context length, image understanding
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
