{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/linvt-empower-your-image-level-large-language","title":"LinVT: Empower Your Image-level Large Language Model to Understand Videos","arxiv_id":"2412.05185","date":"2024-12-06","proceeding":null,"authors":["Lishuai Gao","Yujie Zhong","Yingsen Zeng","Haoxian Tan","Dengjie Li","Zheng Zhao"],"abstract":"Large Language Models (LLMs) have been widely used in various tasks, motivating us to develop an LLM-based assistant for videos. Instead of training from scratch, we propose a module to transform arbitrary well-trained image-based LLMs into video-LLMs (after being trained on video data). To better adapt image-LLMs for processing videos, we introduce two design principles: linear transformation to preserve the original visual-language alignment and representative information condensation from redundant video content. Guided by these principles, we propose a plug-and-play Linear Video Tokenizer(LinVT), which enables existing image-LLMs to understand videos. We benchmark LinVT with six recent visual LLMs: Aquila, Blip-3, InternVL2, Mipha, Molmo and Qwen2-VL, showcasing the high compatibility of LinVT. LinVT-based LLMs achieve state-of-the-art performance across various video benchmarks, illustrating the effectiveness of LinVT in multi-modal video understanding.","url_abs":"https://arxiv.org/abs/2412.05185v2","url_pdf":"https://arxiv.org/pdf/2412.05185v2.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":"linvt-empower-your-image-level-large-language","repo_url":"https://github.com/gls0425/linvt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"visual-question-answering-1","task_name":"Visual 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-mvbench","task":"Video Question Answering","dataset":"MVBench","model":"LinVT-Qwen2-VL\n(7B)","rank_in_archive_order":1,"of":22,"metrics":{"Avg.":"69.3"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-next-qa","task":"Video Question Answering","dataset":"NExT-QA","model":"LinVT-Qwen2-VL\n(7B)","rank_in_archive_order":1,"of":47,"metrics":{"Accuracy":"85.5"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"LinVT","rank_in_archive_order":225,"of":231,"metrics":{"GPT-4 score":"23.5"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-activitynet","task":"Zero-Shot Video Question Answer","dataset":"ActivityNet-QA","model":"LinVT-Qwen2-VL(7B)","rank_in_archive_order":4,"of":28,"metrics":{"Accuracy":"60.1","Confidence Score":"3.6"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-egoschema-1","task":"Zero-Shot Video Question Answer","dataset":"EgoSchema (fullset)","model":"LinVT-Qwen2-VL(7B)","rank_in_archive_order":2,"of":29,"metrics":{"Accuracy":"69.5"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-msrvtt-qa","task":"Zero-Shot Video Question Answer","dataset":"MSRVTT-QA","model":"LinVT-Qwen2-VL\n(7B)","rank_in_archive_order":6,"of":30,"metrics":{"Accuracy":"66.2","Confidence Score":"4.0"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-msvd-qa","task":"Zero-Shot Video Question Answer","dataset":"MSVD-QA","model":"LinVT-Qwen2-VL\n(7B)","rank_in_archive_order":3,"of":28,"metrics":{"Accuracy":"80.2","Confidence Score":"4.4"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-tgif-qa","task":"Zero-Shot Video Question Answer","dataset":"TGIF-QA","model":"LinVT-Qwen2-VL\n(7B)","rank_in_archive_order":2,"of":14,"metrics":{"Accuracy":"81.3","Confidence Score":"4.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.05185","atlas_url":"https://app.syntology.ai/?focus=2412.05185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05185"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gls0425/linvt","reach":{"status":"ok"}}],"summary":{"ran_honours":2,"ran_fixture":1,"ran_violates":1,"unverified":8},"by_repo_kind":{"official":{"samples":9,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":12,"samples":[{"code_sha256_prefix":"e159a001bd4cbfaa","entry":"evaluate_exact_match_accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"e159a001bd4cbfaa"}},{"code_sha256_prefix":"4ffcad52354b4806","entry":"evaluate_relaxed_accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"4ffcad52354b4806"}},{"code_sha256_prefix":"bd77f5f8067f18e9","entry":"find_closest_aspect_ratio","repo":"gls0425/linvt","repo_kind":"official","path":"streamlit_demo/model_worker.py","file_url":"https://github.com/gls0425/linvt/blob/HEAD/streamlit_demo/model_worker.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bd77f5f8067f18e9"}},{"code_sha256_prefix":"b3c8680ebd8739af","entry":"relaxed_correctness","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"b3c8680ebd8739af"}},{"code_sha256_prefix":"bb1a26fe42d7075c","entry":"allreduce_hook","repo":"gls0425/linvt","repo_kind":"official","path":"classification/ddp_hooks.py","file_url":"https://github.com/gls0425/linvt/blob/HEAD/classification/ddp_hooks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bb1a26fe42d7075c"}},{"code_sha256_prefix":"21bd5be56c8f79d0","entry":"bf16_compress_hook","repo":"gls0425/linvt","repo_kind":"official","path":"classification/ddp_hooks.py","file_url":"https://github.com/gls0425/linvt/blob/HEAD/classification/ddp_hooks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"21bd5be56c8f79d0"}},{"code_sha256_prefix":"8c4fa54e6e3b7fb7","entry":"build_scheduler","repo":"gls0425/linvt","repo_kind":"official","path":"classification/lr_scheduler.py","file_url":"https://github.com/gls0425/linvt/blob/HEAD/classification/lr_scheduler.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8c4fa54e6e3b7fb7"}},{"code_sha256_prefix":"45fcbc909d30fb3b","entry":"create_logger","repo":"gls0425/linvt","repo_kind":"official","path":"classification/logger.py","file_url":"https://github.com/gls0425/linvt/blob/HEAD/classification/logger.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"45fcbc909d30fb3b"}},{"code_sha256_prefix":"26bfffb625dfe211","entry":"fp16_compress_hook","repo":"gls0425/linvt","repo_kind":"official","path":"classification/ddp_hooks.py","file_url":"https://github.com/gls0425/linvt/blob/HEAD/classification/ddp_hooks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"26bfffb625dfe211"}},{"code_sha256_prefix":"e452206cf1a59c19","entry":"get_config","repo":"gls0425/linvt","repo_kind":"official","path":"classification/config.py","file_url":"https://github.com/gls0425/linvt/blob/HEAD/classification/config.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e452206cf1a59c19"}},{"code_sha256_prefix":"0dde2e782959c0bd","entry":"load_image_from_base64","repo":"gls0425/linvt","repo_kind":"official","path":"streamlit_demo/model_worker.py","file_url":"https://github.com/gls0425/linvt/blob/HEAD/streamlit_demo/model_worker.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0dde2e782959c0bd"}},{"code_sha256_prefix":"2dcfa48e398dddca","entry":"sa_flops","repo":"gls0425/linvt","repo_kind":"official","path":"classification/gflops.py","file_url":"https://github.com/gls0425/linvt/blob/HEAD/classification/gflops.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2dcfa48e398dddca"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}