{"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/bimba-selective-scan-compression-for-long","title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering","arxiv_id":"2503.09590","date":"2025-03-12","proceeding":"CVPR 2025 1","authors":["Md Mohaiminul Islam","Tushar Nagarajan","Huiyu Wang","Gedas Bertasius","Lorenzo Torresani"],"abstract":"Video Question Answering (VQA) in long videos poses the key challenge of extracting relevant information and modeling long-range dependencies from many redundant frames. The self-attention mechanism provides a general solution for sequence modeling, but it has a prohibitive cost when applied to a massive number of spatiotemporal tokens in long videos. Most prior methods rely on compression strategies to lower the computational cost, such as reducing the input length via sparse frame sampling or compressing the output sequence passed to the large language model (LLM) via space-time pooling. However, these naive approaches over-represent redundant information and often miss salient events or fast-occurring space-time patterns. In this work, we introduce BIMBA, an efficient state-space model to handle long-form videos. Our model leverages the selective scan algorithm to learn to effectively select critical information from high-dimensional video and transform it into a reduced token sequence for efficient LLM processing. Extensive experiments demonstrate that BIMBA achieves state-of-the-art accuracy on multiple long-form VQA benchmarks, including PerceptionTest, NExT-QA, EgoSchema, VNBench, LongVideoBench, and Video-MME. Code, and models are publicly available at https://sites.google.com/view/bimba-mllm.","url_abs":"https://arxiv.org/abs/2503.09590v1","url_pdf":"https://arxiv.org/pdf/2503.09590v1.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":"bimba-selective-scan-compression-for-long","repo_url":"https://github.com/md-mohaiminul/BIMBA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-next-qa","task":"Video Question Answering","dataset":"NExT-QA","model":"BIMBA-LLaVA-Qwen2-7B","rank_in_archive_order":5,"of":47,"metrics":{"Accuracy":"83.73"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-perception-test","task":"Video Question Answering","dataset":"Perception Test","model":"BIMBA-LLaVA-Qwen2-7B","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy (Top-1)":"68.51"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-egoschema-1","task":"Zero-Shot Video Question Answer","dataset":"EgoSchema (fullset)","model":"BIMBA-LLaVA-Qwen2-7B","rank_in_archive_order":1,"of":29,"metrics":{"Accuracy":"71.14"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-vnbench","task":"Zero-Shot Video Question Answer","dataset":"VNBench","model":"BIMBA-LLaVA-Qwen2-7B","rank_in_archive_order":1,"of":9,"metrics":{"Accuracy":"77.88"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-video-mme-1","task":"Zero-Shot Video Question Answer","dataset":"Video-MME","model":"BIMBA-LLaVA-Qwen2-7B","rank_in_archive_order":6,"of":11,"metrics":{"Accuracy (%)":"64.67"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.09590","atlas_url":"https://app.syntology.ai/?focus=2503.09590","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":"2503.09590"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2503.09590\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2503.09590"},"call":"get_concepts_for_paper(arxiv_id=\"2503.09590\")"}],"by_repo":[{"repo":"md-mohaiminul/BIMBA","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"f9ab6fac49e959a3fd5196a5934a2686bb87634a1973502a72d4d931a6bc6198","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}