Papers › TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding

TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding

4 Dec 2023CVPR 2024 1arXiv:2312.02051archive 2025-07-28

Shuhuai Ren, Linli Yao, Shicheng Li, Xu sun, Lu Hou

This work proposes TimeChat, a time-sensitive multimodal large language model specifically designed for long video understanding. Our model incorporates two key architectural contributions: (1) a timestamp-aware frame encoder that binds visual content with the timestamp of each frame, and (2) a sliding video Q-Former that produces a video token sequence of varying lengths to accommodate videos of various durations. Additionally, we construct an instruction-tuning dataset, encompassing 6 tasks and a total of 125K instances, to further enhance TimeChat's instruction-following performance. Experiment results across various video understanding tasks, such as dense captioning, temporal grounding, and highlight detection, demonstrate TimeChat's strong zero-shot temporal localization and reasoning capabilities. For example, it achieves +9.2 F1 score and +2.8 CIDEr on YouCook2, +5.8 HIT@1 on QVHighlights, and +27.5 R@1 (IoU=0.5) on Charades-STA, compared to state-of-the-art video large language models, holding the potential to serve as a versatile video assistant for long-form video comprehension tasks and satisfy realistic user requirements.

PaperPDFConference PDFCodeCode 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

No sample from the archive's official repository (renshuhuai-andy/timechat) is linked to this paper; the 11 samples below come from 1 community repository. Syntology harvested code from renshuhuai-andy/timechat for another paper.

renshuhuai-andy/timechat: Syntology's graph links these samples to TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos (arXiv:2504.17343; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method.

Syntology 11 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 11 samples from 1 repository, 10 ran (5 with no instrument failure; 5 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 10 samples that ran have no recorded date.

renshuhuai-andy/timechat officialmentioned in papermentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos (arXiv:2504.17343; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
lntzm/cvpr24track-longvideo mentioned on GitHubpytorchBSD-3-ClauseSyntology: 11 samples, 10 ran (5 instrument-failed) · 1 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
4ran · our draft was wrong
1ran; the contract check could not run
4ran
1unverified

Licence: 1 of the 11 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from lntzm/cvpr24track-longvideo. “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.

lntzm/cvpr24track-longvideo community (archive-listed) 11 samples, 10 ran (5 instrument-failed) · 1 unverified
apply_rotary_pos_emb in 393 papers
census: 14 implementations from 15 papers, 8 distinct outputs across 7 buckets, one shared input per bucket
timechat/models/modeling_llama.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant BSD-3-Clause (permissive) · d61c483a3c2b3156 · report fixture: signature q:Tensor/4/float, k:Tensor/4/float, cos:Tensor/2/float, sin:Tensor/2/float, position_ids:Tensor/2/int, unsqueeze_dim:int/0/int · returned tuple · level recorded, date not recorded
check_ans in 6 papers benchmark/evaluate_mvbench.py ran fingerprinted BSD-3-Clause (permissive) · f9970c764c5e259d · report fixture: signature pred:str/0/str, gt:str/0/str · returned bool · level recorded 2026-09-25
disabled_train in 172 papers timechat/models/blip2.py ran · violated contract BSD-3-Clause (permissive) · 4cb732f513d69dfd · report fixture: signature self:callable/0/?, mode:bool/0/bool · returned SimpleModel · level recorded, date not recorded
extract_answer in 112 papers benchmark/evaluate_egoschema.py ran fingerprinted BSD-3-Clause (permissive) · 8c3317746d989d00 · report fixture: signature llm_message:str/0/str · returned int · level recorded 2026-09-24
load_data in 700 papers evaluate.py ran BSD-3-Clause (permissive) · 741e5b0b3aa32a32 · report fixture: signature args:Args/0/?, anno_path:str/0/str, split:str/0/str · returned list · level recorded 2026-09-24
merge_seg_caps evaluate.py ran · our draft was wrong BSD-3-Clause (permissive) · d650b26a59df9e29 · report fixture: signature results:list/1/dict · returned dict · level recorded 2026-09-24
prepare_input_output_pairs utils/compress_video_data.py ran BSD-3-Clause (permissive) · 71a5b262cd33e2d0 · report fixture: signature input_root:str/0/str, output_root:str/0/str, input_file_list_path:str/0/str · returned tuple · level recorded 2026-09-24
read_txt in 41 papers evaluate.py ran · our draft was wrong BSD-3-Clause (permissive) · e49f0cf401af904b · report fixture: signature path:str/0/str · returned str · level recorded 2026-09-24
rotate_half in 424 papers
census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
timechat/models/modeling_llama.py ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · b99eea6376d1e212 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
tile in 109 papers
census: 5 implementations from 7 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
timechat/models/base_model.py ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) here; the stored copy is pointer only · cb33571427334815 · report fixture: signature x:Tensor/4/float, dim:int/0/int, n_tile:int/0/int · returned Tensor · level recorded 2026-09-24
all_gather_with_grad in 93 papers timechat/models/base_model.py unverified BSD-3-Clause (permissive) · 0ec9fc2025c16f65 · report

Tasks

Dense CaptioningHighlight DetectionInstruction FollowingLanguage ModelingLanguage ModellingLarge Language ModelMultimodal Large Language ModelTemporal LocalizationVideo Question AnsweringVideo UnderstandingVideo-Text RetrievalZero-Shot Video Question Answer

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Question Answering MVBench TimeChat Avg. 38.5 #16 of 22 Archive leaderboard report
Video Question Answering OVBench TimeChat (7B) AVG 12.8 #15 of 16 Archive leaderboard report
Video-Text Retrieval Test-of-Time Time-Chat 2-Class Accuracy 76.67 #2 of 4 Archive leaderboard report
Zero-Shot Video Question Answer EgoSchema (fullset) TimeChat (7B) Accuracy 33.0 #24 of 29 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