{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/internvideo2-5-empowering-video-mllms-with","title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","arxiv_id":"2501.12386","date":"2025-01-21","proceeding":null,"authors":["Yi Wang","Xinhao Li","Ziang Yan","Yinan He","Jiashuo Yu","Xiangyu Zeng","Chenting Wang","Changlian Ma","Haian Huang","Jianfei Gao","Min Dou","Kai Chen","Wenhai Wang","Yu Qiao","Yali Wang","LiMin Wang"],"abstract":"This paper aims to improve the performance of video multimodal large language models (MLLM) via long and rich context (LRC) modeling. As a result, we develop a new version of InternVideo2.5 with a focus on enhancing the original MLLMs' ability to perceive fine-grained details and capture long-form temporal structure in videos. Specifically, our approach incorporates dense vision task annotations into MLLMs using direct preference optimization and develops compact spatiotemporal representations through adaptive hierarchical token compression. Experimental results demonstrate this unique design of LRC greatly improves the results of video MLLM in mainstream video understanding benchmarks (short & long), enabling the MLLM to memorize significantly longer video inputs (at least 6x longer than the original), and master specialized vision capabilities like object tracking and segmentation. Our work highlights the importance of multimodal context richness (length and fineness) in empowering MLLM's innate abilites (focus and memory), providing new insights for future research on video MLLM. Code and models are available at https://github.com/OpenGVLab/InternVideo/tree/main/InternVideo2.5","url_abs":"https://arxiv.org/abs/2501.12386v2","url_pdf":"https://arxiv.org/pdf/2501.12386v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"internvideo2-5-empowering-video-mllms-with","repo_url":"https://github.com/opengvlab/internvideo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"referring-video-object-segmentation","task_name":"Referring Video Object Segmentation"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/referring-expression-segmentation-on-refer-1","task":"Referring Expression Segmentation","dataset":"Refer-YouTube-VOS (2021 public validation)","model":"InternVideo2.5","rank_in_archive_order":33,"of":33,"metrics":{"J&F":"34.2"},"uses_additional_data":false},{"leaderboard":"/sota/referring-video-object-segmentation-on-mevis","task":"Referring Video Object Segmentation","dataset":"MeViS","model":"InternVideo2.5","rank_in_archive_order":12,"of":16,"metrics":{"J&F":"32"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2501.12386","atlas_url":"https://app.syntology.ai/?focus=2501.12386","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2501.12386"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2501.12386\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2501.12386"},"call":"get_concepts_for_paper(arxiv_id=\"2501.12386\")"}],"by_repo":[{"repo":"opengvlab/internvideo","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2212.03191"],"harvested_for_calls":[{"arxiv_id":"2212.03191","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2212.03191"},"call":"get_harvested_code_for_paper(arxiv_id=\"2212.03191\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"6242609b225ee5a81431b85735fd256ffb0fd34830d2e7316677ce3b26389bc8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}