{"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/video-lavit-unified-video-language-pre","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","arxiv_id":"2402.03161","date":"2024-02-05","proceeding":null,"authors":["Yang Jin","Zhicheng Sun","Kun Xu","Liwei Chen","Hao Jiang","Quzhe Huang","Chengru Song","Yuliang Liu","Di Zhang","Yang song","Kun Gai","Yadong Mu"],"abstract":"In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos. Compared to static images, video poses unique challenges for effective large-scale pre-training due to the modeling of its spatiotemporal dynamics. In this paper, we address such limitations in video-language pre-training with an efficient video decomposition that represents each video as keyframes and temporal motions. These are then adapted to an LLM using well-designed tokenizers that discretize visual and temporal information as a few tokens, thus enabling unified generative pre-training of videos, images, and text. At inference, the generated tokens from the LLM are carefully recovered to the original continuous pixel space to create various video content. Our proposed framework is both capable of comprehending and generating image and video content, as demonstrated by its competitive performance across 13 multimodal benchmarks in image and video understanding and generation. Our code and models are available at https://video-lavit.github.io.","url_abs":"https://arxiv.org/abs/2402.03161v3","url_pdf":"https://arxiv.org/pdf/2402.03161v3.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":"video-lavit-unified-video-language-pre","repo_url":"https://github.com/jy0205/lavit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"science-question-answering","task_name":"Science Question Answering"},{"task_slug":"text-to-video-generation","task_name":"Text-to-Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/science-question-answering-on-scienceqa","task":"Science Question Answering","dataset":"ScienceQA","model":"Video-LaVIT","rank_in_archive_order":10,"of":10,"metrics":{"Avg. Accuracy":"70.0"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-video-generation-on-msr-vtt","task":"Text-to-Video Generation","dataset":"MSR-VTT","model":"Video-LaVIT","rank_in_archive_order":3,"of":18,"metrics":{"CLIPSIM":"0.3012","FID":"11.27","FVD":"188.36"},"uses_additional_data":false},{"leaderboard":"/sota/video-generation-on-ucf-101","task":"Video Generation","dataset":"UCF-101","model":"Video-LaVIT","rank_in_archive_order":20,"of":48,"metrics":{"FVD16":"280.57","Inception Score":"44.26"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"Video-LaVIT","rank_in_archive_order":175,"of":231,"metrics":{"GPT-4 score":"33.2","Params":"7B"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mmbench","task":"Visual Question Answering","dataset":"MMBench","model":"Video-LaVIT","rank_in_archive_order":4,"of":5,"metrics":{"GPT-3.5 score":"67.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-gqa-test-dev","task":"Visual Question Answering (VQA)","dataset":"GQA test-dev","model":"Video-LaVIT","rank_in_archive_order":4,"of":17,"metrics":{"Accuracy":"64.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vizwiz-2020-vqa","task":"Visual Question Answering (VQA)","dataset":"VizWiz 2020 VQA","model":"Video-LaVIT","rank_in_archive_order":5,"of":16,"metrics":{"overall":"56.0"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-activitynet","task":"Zero-Shot Video Question Answer","dataset":"ActivityNet-QA","model":"Video-LaVIT","rank_in_archive_order":13,"of":28,"metrics":{"Accuracy":"50.1","Confidence Score":"3.3"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-msrvtt-qa","task":"Zero-Shot Video Question Answer","dataset":"MSRVTT-QA","model":"Video-LaVIT","rank_in_archive_order":16,"of":30,"metrics":{"Accuracy":"59.3","Confidence Score":"3.3"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-msvd-qa","task":"Zero-Shot Video Question Answer","dataset":"MSVD-QA","model":"Video-LaVIT","rank_in_archive_order":14,"of":28,"metrics":{"Accuracy":"73.2","Confidence Score":"3.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.03161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03161"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/jy0205/lavit","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":2,"ran":1,"unverified":2},"by_repo_kind":{"listed":{"samples":5,"ran":3,"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":5,"samples":[{"code_sha256_prefix":"dcd422d66b0581d8","entry":"get_cast_dtype","repo":"jy0205/lavit","repo_kind":"listed","path":"LaVIT/models/modeling_visual_encoder.py","file_url":"https://github.com/jy0205/lavit/blob/HEAD/LaVIT/models/modeling_visual_encoder.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"code_sha256_prefix":"eca6cdf05972a95e","entry":"l2norm","repo":"jy0205/lavit","repo_kind":"listed","path":"LaVIT/models/modeling_visual_tokenzier.py","file_url":"https://github.com/jy0205/lavit/blob/HEAD/LaVIT/models/modeling_visual_tokenzier.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eca6cdf05972a95e"}},{"code_sha256_prefix":"58629c6a6cb6b282","entry":"save_result","repo":"jy0205/lavit","repo_kind":"listed","path":"LaVIT/utils.py","file_url":"https://github.com/jy0205/lavit/blob/HEAD/LaVIT/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"58629c6a6cb6b282"}},{"code_sha256_prefix":"147a64aa5ec21268","entry":"build_eva_clip","repo":"jy0205/lavit","repo_kind":"listed","path":"LaVIT/models/modeling_visual_encoder.py","file_url":"https://github.com/jy0205/lavit/blob/HEAD/LaVIT/models/modeling_visual_encoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"147a64aa5ec21268"}},{"code_sha256_prefix":"643539116e049080","entry":"download_cached_file","repo":"jy0205/lavit","repo_kind":"listed","path":"LaVIT/utils.py","file_url":"https://github.com/jy0205/lavit/blob/HEAD/LaVIT/utils.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":"643539116e049080"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}