Papers › Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization

Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization

5 Feb 2024arXiv:2402.03161archive 2025-07-28

Yang Jin, Zhicheng Sun, Kun Xu, Liwei Chen, Hao Jiang, Quzhe Huang, Chengru Song, Yuliang Liu, Di Zhang, Yang song, Kun Gai, Yadong Mu

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 5 code samples harvested from 1 repository linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 5 samples from 1 repository, 3 ran (1 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 3 samples that ran have no recorded date.

jy0205/lavit mentioned on GitHubpytorchNOASSERTIONSyntology: 5 samples, 3 ran (2 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

5 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
1ran
2unverified

Licence: 5 of the 5 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from jy0205/lavit. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives 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” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

jy0205/lavit community (archive-listed) 5 samples, 3 ran (2 instrument-failed) · 2 unverified
get_cast_dtype in 67 papers LaVIT/models/modeling_visual_encoder.py ran · our draft was wrong no licence file found · pointer only · dcd422d66b0581d8 · report fixture: signature precision:str/0/str · returned dtype · level recorded, date not recorded
l2norm in 84 papers
census: 12 implementations from 20 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
LaVIT/models/modeling_visual_tokenzier.py ran · our draft was wrong fingerprinted no licence file found · pointer only · eca6cdf05972a95e · report fixture: signature t:Tensor/2/float · returned Tensor · level recorded, date not recorded
save_result in 10 papers LaVIT/utils.py ran no licence file found · pointer only · 58629c6a6cb6b282 · report fixture: signature result:list/1/dict, result_dir:str/0/str, filename:str/0/str, remove_duplicate:str/0/str · returned str · level recorded 2026-09-24
build_eva_clip LaVIT/models/modeling_visual_encoder.py unverified licence not identified · pointer only · 147a64aa5ec21268 · report
download_cached_file in 40 papers LaVIT/utils.py unverified no licence file found · pointer only · 643539116e049080 · report

Tasks

Science Question AnsweringText-to-Video GenerationVideo GenerationVisual Question AnsweringVisual Question Answering (VQA)Zero-Shot Video Question Answer

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Science Question Answering ScienceQA Video-LaVIT Avg. Accuracy 70.0 #10 of 10 Archive leaderboard report
Text-to-Video Generation MSR-VTT Video-LaVIT CLIPSIM 0.3012 #3 of 18 Archive leaderboard report
Text-to-Video Generation MSR-VTT Video-LaVIT FID 11.27 #3 of 18 Archive leaderboard report
Text-to-Video Generation MSR-VTT Video-LaVIT FVD 188.36 #3 of 18 Archive leaderboard report
Video Generation UCF-101 Video-LaVIT FVD16 280.57 #20 of 48 Archive leaderboard report
Video Generation UCF-101 Video-LaVIT Inception Score 44.26 #20 of 48 Archive leaderboard report
Visual Question Answering MM-Vet Video-LaVIT GPT-4 score 33.2 #175 of 231 Archive leaderboard report
Visual Question Answering MM-Vet Video-LaVIT Params 7B #175 of 231 Archive leaderboard report
Visual Question Answering MMBench Video-LaVIT GPT-3.5 score 67.3 #4 of 5 Archive leaderboard report
Visual Question Answering (VQA) GQA test-dev Video-LaVIT Accuracy 64.4 #4 of 17 Archive leaderboard report
Visual Question Answering (VQA) VizWiz 2020 VQA Video-LaVIT overall 56.0 #5 of 16 Archive leaderboard report
Zero-Shot Video Question Answer ActivityNet-QA Video-LaVIT Accuracy 50.1 #13 of 28 Archive leaderboard report
Zero-Shot Video Question Answer ActivityNet-QA Video-LaVIT Confidence Score 3.3 #13 of 28 Archive leaderboard report
Zero-Shot Video Question Answer MSRVTT-QA Video-LaVIT Accuracy 59.3 #16 of 30 Archive leaderboard report
Zero-Shot Video Question Answer MSRVTT-QA Video-LaVIT Confidence Score 3.3 #16 of 30 Archive leaderboard report
Zero-Shot Video Question Answer MSVD-QA Video-LaVIT Accuracy 73.2 #14 of 28 Archive leaderboard report
Zero-Shot Video Question Answer MSVD-QA Video-LaVIT Confidence Score 3.9 #14 of 28 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections