Papers › GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation

GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation

10 Apr 2025CVPR 2025 1arXiv:2504.07962archive 2025-07-28

Lang Lin, Xueyang Yu, Ziqi Pang, Yu-Xiong Wang

This paper proposes a novel framework utilizing multi-modal large language models (MLLMs) for referring video object segmentation (RefVOS). Previous MLLM-based methods commonly struggle with the dilemma between "Ref" and "VOS": they either specialize in understanding a few key frames (global reasoning) or tracking objects on continuous frames (local reasoning), and rely on external VOS or frame selectors to mitigate the other end of the challenge. However, our framework GLUS shows that global and local consistency can be unified into a single video segmentation MLLM: a set of sparse "context frames" provides global information, while a stream of continuous "query frames" conducts local object tracking. This is further supported by jointly training the MLLM with a pre-trained VOS memory bank to simultaneously digest short-range and long-range temporal information. To improve the information efficiency within the limited context window of MLLMs, we introduce object contrastive learning to distinguish hard false-positive objects and a self-refined framework to identify crucial frames and perform propagation. By collectively integrating these insights, our GLUS delivers a simple yet effective baseline, achieving new state-of-the-art for MLLMs on the MeViS and Ref-Youtube-VOS benchmark. Our project page is at https://glus-video.github.io/.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 12 code samples harvested from 1 repository linked to this paper: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 12 samples from 1 repository, 3 ran (3 with no instrument failure; 0 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

GLUS-video/GLUS mentioned on GitHubpytorchSyntology: 12 samples, 3 ran (0 instrument-failed) · 9 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

12 samples harvested: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. “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.

3ran
9unverified

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 GLUS-video/GLUS. “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.

GLUS-video/GLUS community (archive-listed) 12 samples, 3 ran (0 instrument-failed) · 9 unverified
ContrastiveLoss in 16 papers model/GLUS.py ran no licence file found · pointer only · fafc49e646cbb27e · report fixture: returned ContrastiveLoss · level recorded 2026-09-22
LlavaLlamaModel in 13 papers model/GLUS.py ran no licence file found · pointer only · fd826b7940bc9b38 · report fixture: returned LlavaLlamaModel · level recorded 2026-09-22
segTokenBank model/GLUS.py ran no licence file found · pointer only · c07b53902191d016 · report fixture: returned segTokenBank · level recorded 2026-09-22
GLUSForCausalLM model/GLUS.py unverified no licence file found · pointer only · f336c18e86b8d8a3 · report
GlusMetaModel model/GLUS.py unverified no licence file found · pointer only · 78b6a27c210c8801 · report
GlusModel model/GLUS.py unverified no licence file found · pointer only · 5cfd95bfb0a02aaa · report
LlavaLlamaForCausalLM in 15 papers model/GLUS.py unverified no licence file found · pointer only · b77d0b4e10b306e7 · report
LlavaMetaForCausalLM in 16 papers model/GLUS.py unverified no licence file found · pointer only · 65e399d0eab7c33e · report
LlavaMetaModel in 16 papers model/GLUS.py unverified no licence file found · pointer only · 9fb467589b9d20f5 · report
SAM2Transforms model/GLUS.py unverified no licence file found · pointer only · 3f123a3de662ff17 · report
_load_checkpoint model/GLUS.py unverified no licence file found · pointer only · 9ad65f1c27158aa9 · report
build_sam2 in 17 papers model/GLUS.py unverified no licence file found · pointer only · eb1cf9ae06cf7744 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for GLUS (graph method: GLUS). 16 bricks; individually on a fixture: 6 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 10 unverified. The assembly has not been run end-to-end.

  1. GLUSForCausalLM entry · level 0 · unverified · f336c18e86b8d8a3
  2. ContrastiveLoss loss · level 1 · ran · fafc49e646cbb27e
  3. GlusModel helper · level 0 · unverified · 5cfd95bfb0a02aaa
  4. LlavaLlamaForCausalLM helper · level 0 · unverified · b77d0b4e10b306e7
  5. SAM2Transforms helper · level 0 · unverified · 3f123a3de662ff17
  6. dice_loss loss · level 1 · ran; the contract check could not run · a1c2083ec2eaeb22
  7. sigmoid_ce_loss loss · level 1 · ran; the contract check could not run · a9292f5d89194794
  8. segTokenBank helper · level 1 · ran · c07b53902191d016
  9. GlusMetaModel helper · level 0 · unverified · 78b6a27c210c8801
  10. LlavaLlamaModel helper · level 1 · ran · fd826b7940bc9b38
  11. LlavaConfig helper · level 1 · ran · bbd74464f100863e
  12. LlavaMetaForCausalLM model · level 0 · unverified · 65e399d0eab7c33e
  13. build_sam2 helper · level 0 · unverified · eb1cf9ae06cf7744
  14. LlavaMetaModel helper · level 0 · unverified · 9fb467589b9d20f5
  15. _load_checkpoint helper · level 0 · unverified · 9ad65f1c27158aa9
  16. build_vision_tower helper · level 0 · unverified · f603e54c961dd1f4

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2504.07962") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningLanguage ModelingLanguage ModellingLarge Language ModelObject TrackingReferring Video Object SegmentationSemantic SegmentationVideo Object SegmentationVideo SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Referring Video Object Segmentation Long-RVOS GLUS J&F 36.6 #4 of 7 Archive leaderboard report
Referring Video Object Segmentation Long-RVOS GLUS tIoU 68.4 #4 of 7 Archive leaderboard report
Referring Video Object Segmentation Long-RVOS GLUS vIoU 34.6 #4 of 7 Archive leaderboard report
Referring Video Object Segmentation MeViS GLUS F 54.2 #3 of 16 Archive leaderboard report
Referring Video Object Segmentation MeViS GLUS J 48.5 #3 of 16 Archive leaderboard report
Referring Video Object Segmentation MeViS GLUS J&F 51.3 #3 of 16 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.

Methods

Contrastive LearningSETVOS

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