{"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/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":{"syntology_url":"https://syntology.ai/paper/2402.03161","atlas_url":"https://app.syntology.ai/?focus=2402.03161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03161"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.03161"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.03161"},"call":"get_harvested_code_for_paper(arxiv_id=\"2402.03161\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2402.03161"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2402.03161\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2402.03161"},"call":"get_concepts_for_paper(arxiv_id=\"2402.03161\")"}],"by_repo":[{"repo":"jy0205/lavit","kind":"listed","samples":5,"ran":3,"instrument":2,"unverified":2}],"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","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2402.03161.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2402.03161.svg"},"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},"n_samples":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"listed":{"samples":5,"ran":3,"n_ran_checked":1,"n_instrument":2,"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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":1,"n_ran_without_level_date":2,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","census_is":"Syntology's function-name census ran implementations with this entry name on one shared input per bucket (the positional rank, kind and dtype of each array argument) and counted the distinct output digests (sha256 of the output rounded to 6 decimals). implementations and papers count the compared samples; distinct_outputs counts digests across all buckets; n_buckets is how many shared inputs were used. It is not a statement that any two samples compute one thing, and the name is a string, not an identity.","samples":[{"code_sha256":"dcd422d66b0581d8","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,"signature":"precision:str/0/str","fixture_out_type":"dtype","code_page":"/code/get-cast-dtype","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, jy0205/lavit when it was checked","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"code_sha256":"eca6cdf05972a95e","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,"signature":"t:Tensor/2/float","fixture_out_type":"Tensor","retrieve_with":{"tool":"get_code","code_sha256":"eca6cdf05972a95e"},"code_page":"/code/l2norm","census":{"url":"/census/l2norm","implementations":12,"papers":20,"distinct_outputs":3,"n_buckets":1,"bucket_key":[[2,"float","float32"]],"bucket_index":1,"bucket_label":"arg 1: rank 2, kind float, dtype float32"},"census_bucket_fragment":"bucket-1","licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, jy0205/lavit when it was checked","mcp_get_code":{"code_sha256":"eca6cdf05972a95e"}},{"code_sha256":"58629c6a6cb6b282","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,"signature":"result:list/1/dict, result_dir:str/0/str, filename:str/0/str, remove_duplicate:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/save-result","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, jy0205/lavit when it was checked","mcp_get_code":{"code_sha256":"58629c6a6cb6b282"}},{"code_sha256":"147a64aa5ec21268","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,"code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, jy0205/lavit (NOASSERTION)","mcp_get_code":{"code_sha256":"147a64aa5ec21268"}},{"code_sha256":"643539116e049080","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,"code_page":"/code/download-cached-file","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, jy0205/lavit when it was checked","mcp_get_code":{"code_sha256":"643539116e049080"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"447aca43b6a1e30586d198afb97ee123d0772084729a310b729ff86985ae91f5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}