{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T00:10:51Z","timestamp":1783815051435,"version":"3.55.0"},"reference-count":84,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376031,62372014"],"award-info":[{"award-number":["62376031,62372014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02240","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24170-24181","source":"Crossref","is-referenced-by-count":4,"title":["VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges"],"prefix":"10.1109","author":[{"given":"Yuxuan","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, BIGAI,NLCo Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqi","family":"Song","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, BIGAI,NLCo Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cihang","family":"Xie","sequence":"additional","affiliation":[{"name":"University of California,Computer Science and Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Wangxuan Institute of Computer Technology, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zilong","family":"Zheng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, BIGAI,NLCo Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Memory consolidation enables long-context video understanding","volume":"abs\/2402.05861","author":"Balazevic","year":"2024","journal-title":"CoRR"},{"key":"ref2","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0805"},{"key":"ref5","article-title":"Scaling transformer to 1 m tokens and beyond with RMT","volume":"abs\/2304.11062","author":"Bulatov","year":"2023","journal-title":"CoRR"},{"key":"ref6","article-title":"Video mamba suite: State space model as a versatile alternative for video understanding","volume":"abs\/2403.09626","author":"Chen","year":"2024","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01742"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00967"},{"key":"ref9","article-title":"Egoplanbench: Benchmarking egocentric embodied planning with multimodal large language models","volume":"abs\/2312.06722","author":"Chen","year":"2023","journal-title":"CoRR"},{"key":"ref10","article-title":"Zero-shot video question answering with procedural programs","volume":"abs\/2312.00937","author":"Choudhury","year":"2023","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref12","first-page":"8469","article-title":"Palm-e: An embodied multimodal language model","volume-title":"In International Conference on Machine Learning (ICML)","author":"Driess"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71278-5_12"},{"key":"ref15","author":"Fu","year":"2024","journal-title":"Vita: Towards open-source interactive omni multimodal 11 m"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2017.10.004"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01419"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01282"},{"issue":"1","key":"ref21","first-page":"33","article-title":"Texttiling: Segmenting text into multiparagraph subtopic passages","volume":"23","author":"Hearst","year":"1997","journal-title":"Comput. Linguistics"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_41"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.879"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_16"},{"key":"ref25","article-title":"In search of needles in a 11 m haystack: Recurrent memory finds what 11 ms miss","volume":"abs\/2402.10790","author":"Kuratov","year":"2024","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.29"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3571946"},{"key":"ref28","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.859"},{"key":"ref30","article-title":"Videochat: Chat-centric video understanding","volume":"abs\/2305.06355","author":"Li","year":"2023","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref37","article-title":"World model on million-length video and language with blockwise ringattention","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Liu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01249"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2004"},{"key":"ref42","article-title":"Embodiedgpt: Vision-language pre-training via embodied chain of thought","author":"Mu","year":"2023","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26316-3_29"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01364"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01404"},{"key":"ref46","article-title":"Momentor: Advancing video large language model with fine-grained temporal reasoning","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024","author":"Qian"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3792"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01016"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.403"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00095"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02436"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_9"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0649"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_4"},{"key":"ref59","article-title":"Lifelongmemory: Leveraging 11 ms for answering queries in egocentric videos","volume":"abs\/2312.05269","author":"Wang","year":"2023","journal-title":"CoRR"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.276"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.276"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.556"},{"key":"ref63","article-title":"Exovip: Step-by-step verification and exploration with exoskeleton modules for compositional visual reasoning","volume-title":"The first Conference on Language Modeling (CoLM)","author":"Wang"},{"key":"ref64","article-title":"LVCHAT: facilitating long video comprehension","volume":"abs\/2402.12079","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01763"},{"key":"ref66","article-title":"Tokenswift: Lossless acceleration of ultra long sequence generation","volume-title":"Proceedings of the 42nd International Conference on Machine Learning","author":"Wu"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref69","article-title":"Slot-vlm: Slowfast slots for video-language modeling","author":"Xu","year":"2024","journal-title":"ArXiv"},{"key":"ref70","article-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","volume":"abs\/2404.16994","author":"Xu","year":"2024","journal-title":"CoRR"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref72","article-title":"Doraemongpt: Toward understanding dynamic scenes with large language models","volume":"abs\/2401.08392","author":"Yang","year":"2024","journal-title":"CoRR"},{"key":"ref73","article-title":"mplug-owl: Modularization empowers large language models with multimodality","volume":"abs\/2304.14178","author":"Ye","year":"2023","journal-title":"ArXiv"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3354"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1209"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref77","author":"Zhang","year":"2024","journal-title":"Long context transfer from language to vision"},{"key":"ref78","article-title":"LLaMA-adapter: Efficient fine-tuning of large language models with zeroinitialized attention","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhang"},{"key":"ref79","author":"Zhang","year":"2024","journal-title":"Llavanext: A strong zero-shot video understanding model"},{"key":"ref80","article-title":"AntGPT: Can large language models help long-term action anticipation from videos?","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Zhao"},{"key":"ref81","article-title":"MCU: An evaluation framework for open-ended game agents","volume-title":"Proceedings of the 42nd International Conference on Machine Learning","author":"Zheng"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.aacl-main.40"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01727"},{"key":"ref84","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","volume":"abs\/2304.10592","author":"Zhu","year":"2023","journal-title":"ArXiv"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444169.pdf?arnumber=11444169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:12:29Z","timestamp":1777612349000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02240","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}