Papers › LinVT: Empower Your Image-level Large Language Model to Understand Videos

LinVT: Empower Your Image-level Large Language Model to Understand Videos

6 Dec 2024arXiv:2412.05185archive 2025-07-28

Lishuai Gao, Yujie Zhong, Yingsen Zeng, Haoxian Tan, Dengjie Li, Zheng Zhao

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2412.05185")

Code

Syntology Ran 4 of 12 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · violated contract; 1 ran · fixture could not drive it.

By repository: official repository: 9 samples from 1 repository, 1 ran; 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

gls0425/linvt officialmentioned in papermentioned on GitHubpytorch 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

12 samples harvested; 4 ran; 2 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran · honoured contract
1ran · violated contract
1ran · fixture could not drive it
8unverified

Licence: 12 of the 12 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 gls0425/linvt. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

find_closest_aspect_ratio gls0425/linvt/streamlit_demo/model_worker.py official repository ran · fixture could not drive it no licence file found · pointer only · bd77f5f8067f18e9 · report
allreduce_hook gls0425/linvt/classification/ddp_hooks.py official repository unverified no licence file found · pointer only · bb1a26fe42d7075c · report
bf16_compress_hook gls0425/linvt/classification/ddp_hooks.py official repository unverified no licence file found · pointer only · 21bd5be56c8f79d0 · report
build_scheduler gls0425/linvt/classification/lr_scheduler.py official repository unverified no licence file found · pointer only · 8c4fa54e6e3b7fb7 · report
create_logger gls0425/linvt/classification/logger.py official repository unverified no licence file found · pointer only · 45fcbc909d30fb3b · report
fp16_compress_hook gls0425/linvt/classification/ddp_hooks.py official repository unverified no licence file found · pointer only · 26bfffb625dfe211 · report
get_config gls0425/linvt/classification/config.py official repository unverified no licence file found · pointer only · e452206cf1a59c19 · report
load_image_from_base64 gls0425/linvt/streamlit_demo/model_worker.py official repository unverified no licence file found · pointer only · 0dde2e782959c0bd · report
sa_flops gls0425/linvt/classification/gflops.py official repository unverified no licence file found · pointer only · 2dcfa48e398dddca · report
evaluate_exact_match_accuracy identical code first harvested elsewhere ran · honoured contract licence of this copy not recorded · e159a001bd4cbfaa · report
evaluate_relaxed_accuracy identical code first harvested elsewhere ran · honoured contract licence of this copy not recorded · 4ffcad52354b4806 · report
relaxed_correctness identical code first harvested elsewhere ran · violated contract licence of this copy not recorded · b3c8680ebd8739af · report

Tasks

Language ModelingLanguage ModellingLarge Language ModelVideo Question AnsweringVideo UnderstandingVisual Question AnsweringZero-Shot Video Question Answer

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Question Answering MVBench LinVT-Qwen2-VL (7B) Avg. 69.3 #1 of 22 Archive leaderboard report
Video Question Answering NExT-QA LinVT-Qwen2-VL (7B) Accuracy 85.5 #1 of 47 Archive leaderboard report
Visual Question Answering MM-Vet LinVT GPT-4 score 23.5 #225 of 231 Archive leaderboard report
Zero-Shot Video Question Answer ActivityNet-QA LinVT-Qwen2-VL(7B) Accuracy 60.1 #4 of 28 Archive leaderboard report
Zero-Shot Video Question Answer ActivityNet-QA LinVT-Qwen2-VL(7B) Confidence Score 3.6 #4 of 28 Archive leaderboard report
Zero-Shot Video Question Answer EgoSchema (fullset) LinVT-Qwen2-VL(7B) Accuracy 69.5 #2 of 29 Archive leaderboard report
Zero-Shot Video Question Answer MSRVTT-QA LinVT-Qwen2-VL (7B) Accuracy 66.2 #6 of 30 Archive leaderboard report
Zero-Shot Video Question Answer MSRVTT-QA LinVT-Qwen2-VL (7B) Confidence Score 4.0 #6 of 30 Archive leaderboard report
Zero-Shot Video Question Answer MSVD-QA LinVT-Qwen2-VL (7B) Accuracy 80.2 #3 of 28 Archive leaderboard report
Zero-Shot Video Question Answer MSVD-QA LinVT-Qwen2-VL (7B) Confidence Score 4.4 #3 of 28 Archive leaderboard report
Zero-Shot Video Question Answer TGIF-QA LinVT-Qwen2-VL (7B) Accuracy 81.3 #2 of 14 Archive leaderboard report
Zero-Shot Video Question Answer TGIF-QA LinVT-Qwen2-VL (7B) Confidence Score 4.3 #2 of 14 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