Video Token Merging for Long Video Understanding
The DOI matches its Crossref record.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Due to the inherent complexity and resource demands, most current research on long video learning focuses on discriminative tasks such as video understanding [75, 112, 24].”
From Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality (2025) · cites this paper as [75]
Citations
Cites
Still being checked.
Cited by
Kong, Z., Li, Y., Zeng, F., Xin, L., Messica, S., Lin, X., Zhao, P., Kellis, M., Tang, H., & Zitnik, M. (2025) · arXiv · doi:10.48550/arxiv.2505.18227 · Cited by 51
TinyHistory: Lightweight Video History Embeddings Via Two-Stage Context Learning
Zhang, L., Cai, S., Li, M., Zeng, C., Lu, B., Rao, A., Han, S., Wetzstein, G., & Agrawala, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37189-8_10 · Cited by 38
Xu, B., Du, Y., Liu, Z., Yang, S., Jiang, Z., Yan, S., Saha, R., Pumarola, A., Wang, W., & Li, P. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.21221 · Cited by 17
Mode Seeking meets Mean Seeking for Fast Long Video GenerationPreprint
Cai, S., Nie, W., Liu, C., Berner, J., Zhang, L., Ma, N., Chen, H., Agrawala, M., Guibas, L., Wetzstein, G., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.24289 · Cited by 15
Unifying Specialized Visual Encoders for Video Language ModelsPreprint
Chung, J., Zhu, T., Saez-Diez, M. G., Niebles, J. C., Zhou, H., & Russakovsky, O. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.01426 · Cited by 13
Token Expand-Merge: Training-Free Token Compression for Vision-Language-Action Models
Ye, Y., Ma, J., Cen, J., & Lu, Z. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3703265 · Cited by 12
FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video UnderstandingPreprint
Cho, J., Lee, J., Hayat, M., Hwang, K., Porikli, F., & Choi, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.00141 · Cited by 8
Foveated Diffusion: Efficient Spatially Adaptive Image and Video GenerationPreprint
Chao, B., Yariv, L., Xiao, H., & Wetzstein, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.23491 · Cited by 8
Mitigating Semantic Collapse in Partially Relevant Video Retrieval
Moon, W., Jung, M., Park, G., Kim, T., Cho, C.-H., Jun, W., & Heo, J. (2025) · neural information processing systems · doi:10.52202/085713-0783 · Cited by 6
CodecSight: Leveraging Video Codec Signals for Efficient Streaming VLM InferencePreprint
Zou, Y., Chen, W., Chen, Y., Rajan, A., Park, J., Nitin, S., Tao, L., Romero, F., & Ustiugov, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.06036 · Cited by 6
Video, How do Your Tokens Merge?
Pollard, S., & Wray, M. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00317 · Cited by 4
CubistMerge: Spatial-Preserving Token Merging For Diverse ViT BackbonesPreprint
Gong, W. G., & Lis, M. (2025) · arXiv.org · doi:10.48550/arxiv.2509.21764
Temporal Cluster Assignment for Efficient Real-Time Video SegmentationPreprint
Yung, K.-W., Bragman, F., Xu, J., Luengo, I., Stoyanov, D. V., & Mazomenos, E. B. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.05851
StretchySnake: Flexible SSM Training Unlocks Action Recognition Across Spatio-Temporal ScalesPreprint
Siddiqui, N., Gupta, R., Swetha, S., & Shah, M. A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.16209
UniAPO: Unified Multimodal Automated Prompt OptimizationPreprint
Zhu, Q., Chen, Y., Zhong, H., Li, Y., Chen, J., Zhang, Z., Zhang, J., & Yang, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.17890
Self-citationToken Merging via Spatiotemporal Information Mining for Surgical Video UnderstandingPreprint
Jiang, X., Yang, C., Zhang, D., Dong, P., Yang, X., & Cheng, K.-T. T. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.23672
Entropy-Guided Condensing for Vision Transformer
Lin, S., Lyu, P., Liu, D., Li, Z., Wang, W., Chang, X., & Zheng, Y. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02753-y
V-Nutri: Dish-Level Nutrition Estimation from Egocentric Cooking VideosPreprint
Yue, C., Xu, C., & He, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.11913
MetaFusion: Instance-Aware Meta-Prompting and Token Refinement for VLMs Generalization
Liu, M., Wu, F., Lu, Z., Wang, Z., Yu, Y., Han, J., & Zhang, Z. M. (2026) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2026.3686093
Self-citationSURGE: Surprise-guided token reduction for efficient video understanding with VLMs
Tang, C., Ek, S., Koch, D., Mullins, R., Weddell, A. S., & Chauhan, J. (2026) · ePrints Soton (University of Southampton)
P-JEPA: Procedural Video Representation Learning via Joint Embedding Predictive ArchitecturePreprint
Tristram, F., Gasperini, S., Killeen, B., Walch, M., Benz, C., Navab, N., & Ghazaei, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.23256
Coreview: Compact Yet Complete Video Representation
Roy, S., Kaushik, A. R., Ratha, N., & Govindaraju, V. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630368
VETO: Video Efficient Token Optimization for Vision Language ModelsPreprint
Faure, G. J., Wang, H., Chen, M.-H., & Hsu, W. H. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.01785
FrameScout: Scouting Query-Relevant Frames for Long Video UnderstandingPreprint
Hu, H., Chen, S., Jiang, W., Gao, L., Kwok, J., & Zhang, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.23975
Metadata
- Authors
- Lee, S.-H., Wang, J., Zhang, Z., Fan, D., & Li, X.
- Venue
- Advances in Neural Information Processing Systems 37
- Published
- 2024
- Pages
- 13851-13871
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W4415798835
- Cited by
- 2
- References
- 0
- Citations by year
- 2026: 2
- FWCI
- 0.41
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- neural information processing systems (publishedVersion)
- 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, video representation learning, video summarization, video captioning
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.