Papers › TRACE: Temporal Grounding Video LLM via Causal Event Modeling

TRACE: Temporal Grounding Video LLM via Causal Event Modeling

8 Oct 2024arXiv:2410.05643archive 2025-07-28

Yongxin Guo, Jingyu Liu, Mingda Li, Xiaoying Tang, Qingbin Liu, Xi Chen

Video Temporal Grounding (VTG) is a crucial capability for video understanding models and plays a vital role in downstream tasks such as video browsing and editing. To effectively handle various tasks simultaneously and enable zero-shot prediction, there is a growing trend in employing video LLMs for VTG tasks. However, current video LLM-based methods rely exclusively on natural language generation, lacking the ability to model the clear structure inherent in videos, which restricts their effectiveness in tackling VTG tasks. To address this issue, this paper first formally introduces causal event modeling framework, which represents videos as sequences of events, and predict the current event using previous events, video inputs, and textural instructions. Each event consists of three components: timestamps, salient scores, and textual captions. We then propose a novel task-interleaved video LLM called TRACE to effectively implement the causal event modeling framework in practice. The TRACE processes visual frames, timestamps, salient scores, and text as distinct tasks, employing various encoders and decoding heads for each. Task tokens are arranged in an interleaved sequence according to the causal event modeling framework's formulation. Extensive experiments on various VTG tasks and datasets demonstrate the superior performance of TRACE compared to state-of-the-art video LLMs. Our model and code are available at \url{https://github.com/gyxxyg/TRACE}.

PaperPDFCodeCode Syntology ran

In Syntology 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="2410.05643")

Code

Syntology Ran 6 of 16 code samples harvested from 1 repository linked to this paper; 10 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

gyxxyg/trace officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

16 samples harvested; 6 ran; 0 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · fixture could not drive it
5ran
10unverified

Licence: 0 of the 16 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 gyxxyg/TRACE. “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.

load_data gyxxyg/TRACE/trace/eval/evaluate.py official repository ran Apache-2.0 (permissive) · 741e5b0b3aa32a32 · report
merge_scenes gyxxyg/TRACE/trace/mm_utils.py official repository ran Apache-2.0 (permissive) · 4b339b70f2a3e67e · report
merge_scenes_not_exeed_max_scene_num gyxxyg/TRACE/trace/mm_utils.py official repository ran Apache-2.0 (permissive) · 1e366edf3b7d93ae · report
merge_seg_caps gyxxyg/TRACE/trace/eval/evaluate.py official repository ran Apache-2.0 (permissive) · d650b26a59df9e29 · report
read_txt gyxxyg/TRACE/trace/eval/evaluate.py official repository ran Apache-2.0 (permissive) · e49f0cf401af904b · report
split_to_even_chunks gyxxyg/TRACE/trace/trace_trainer.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 10893c4608c08075 · report
TraceMetaForCausalLM gyxxyg/trace/trace/model/trace_arch.py official repository unverified Apache-2.0 (permissive) · fe9f9161144b6f90 · report
build_logger gyxxyg/TRACE/trace/utils.py official repository unverified Apache-2.0 (permissive) · 8dc94b9682ebebf9 · report
get_mm_adapter_state_maybe_zero_3 gyxxyg/TRACE/trace/trace_trainer.py official repository unverified Apache-2.0 (permissive) · bb35e3ac741bb2c9 · report
get_peft_state_maybe_zero_3 gyxxyg/trace/trace/train_mt.py official repository unverified Apache-2.0 (permissive) · fa1225dfac92bc0d · report
get_peft_state_non_lora_maybe_zero_3 gyxxyg/trace/trace/train_mt.py official repository unverified Apache-2.0 (permissive) · 1c53657305b66e9f · report
load_pretrained_model gyxxyg/TRACE/trace/model/builder.py official repository unverified Apache-2.0 (permissive) · a2c9ee5dff5e2278 · report
maybe_zero_3 gyxxyg/TRACE/trace/trace_trainer.py official repository unverified Apache-2.0 (permissive) · 735025744c1ab0cf · report
maybe_zero_3 gyxxyg/trace/trace/train_mt.py official repository unverified Apache-2.0 (permissive) · 616ffbdc154ed2d8 · report
pretty_print_semaphore gyxxyg/TRACE/trace/utils.py official repository unverified Apache-2.0 (permissive) · 37899f22fb191b37 · report
violates_moderation gyxxyg/TRACE/trace/utils.py official repository unverified Apache-2.0 (permissive) · f9939a84b9a65279 · report

Tasks

Text GenerationVideo Understanding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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