Papers › MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding

MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding

8 Apr 2024CVPR 2024 1arXiv:2404.05726archive 2025-07-28

Bo He, Hengduo Li, Young Kyun Jang, Menglin Jia, Xuefei Cao, Ashish Shah, Abhinav Shrivastava, Ser-Nam Lim

With the success of large language models (LLMs), integrating the vision model into LLMs to build vision-language foundation models has gained much more interest recently. However, existing LLM-based large multimodal models (e.g., Video-LLaMA, VideoChat) can only take in a limited number of frames for short video understanding. In this study, we mainly focus on designing an efficient and effective model for long-term video understanding. Instead of trying to process more frames simultaneously like most existing work, we propose to process videos in an online manner and store past video information in a memory bank. This allows our model to reference historical video content for long-term analysis without exceeding LLMs' context length constraints or GPU memory limits. Our memory bank can be seamlessly integrated into current multimodal LLMs in an off-the-shelf manner. We conduct extensive experiments on various video understanding tasks, such as long-video understanding, video question answering, and video captioning, and our model can achieve state-of-the-art performances across multiple datasets. Code available at https://boheumd.github.io/MA-LMM/.

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

Syntology 9 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 7 ran (4 with no instrument failure; 3 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.

boheumd/MA-LMM officialmentioned on GitHubpytorchMITSyntology: 9 samples, 7 ran (3 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

9 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
3ran
2unverified

Licence: 1 of the 9 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 boheumd/MA-LMM. “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.

boheumd/MA-LMM official repository 9 samples, 7 ran (3 instrument-failed) · 2 unverified
generate_caption in 21 papers app/caption.py ran MIT (permissive) · 56f02812d66a0d11 · report fixture: signature model:callable/0/?, image:Tensor/4/float, use_nucleus_sampling:bool/0/bool, num_beams:int/0/int, max_length:int/0/int, min_length:int/0/int · returned list · level recorded 2026-09-24
get_concat_v in 11 papers app/dataset_browser.py ran · our draft was wrong MIT (permissive) · 92f2e16ee0d3a24d · report fixture: signature im1:Image/0/?, im2:Image/0/? · returned Image · level recorded 2026-09-24
read_img in 41 papers app/calculate_coco_features.py ran · honoured contract MIT (permissive) · 13a43a7d815937e6 · report fixture: signature filepath:str/0/str · returned Image · level recorded 2026-09-24
resize_img in 31 papers app/utils.py ran · our draft was wrong MIT (permissive) · 926bb38f979a61ef · report fixture: signature raw_img:Image/0/? · returned Image · level recorded 2026-09-24
resize_img_w in 11 papers app/dataset_browser.py ran MIT (permissive) · f809f2ecf34c1c99 · report fixture: signature raw_img:Image/0/?, new_w:int/0/int · returned Image · level recorded 2026-09-24
sample_dataset in 20 papers app/dataset_browser.py ran MIT (permissive) · 3d4bbb5ca53fd24a · report fixture: signature dataset:MockDataset/0/?, indices:list/1/int · returned list · level recorded 2026-09-24
tile in 109 papers
census: 5 implementations from 7 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
lavis/models/base_model.py ran · our draft was wrong fingerprinted MIT (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 lavis/models/base_model.py unverified MIT (permissive) · 0ec9fc2025c16f65 · report
compute_gradcam_batch in 11 papers app/multimodal_search.py unverified MIT (permissive) · 3e12ea8c09674aa8 · report

Tasks

Multiple-choiceQuestion AnsweringTemporal Relation ExtractionVideo CaptioningVideo ClassificationVideo Question AnsweringVideo UnderstandingVisual Question Answering (VQA)

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Temporal Relation Extraction Vinoground MA-LMM-Vicuna-7B Group Score 6.8 #17 of 24 Archive leaderboard report
Temporal Relation Extraction Vinoground MA-LMM-Vicuna-7B Text Score 23.8 #17 of 24 Archive leaderboard report
Temporal Relation Extraction Vinoground MA-LMM-Vicuna-7B Video Score 25.6 #17 of 24 Archive leaderboard report
Video Captioning YouCook2 MA-LMM CIDEr 1.31 #14 of 14 Archive leaderboard report
Video Captioning YouCook2 MA-LMM METEOR 17.6 #14 of 14 Archive leaderboard report
Video Classification Breakfast MA-LMM Accuracy (%) 93.0 #2 of 9 Archive leaderboard report
Video Classification COIN MA-LMM Accuracy (%) 93.2 #2 of 7 Archive leaderboard report
Video Question Answering ActivityNet-QA MA-LMM Accuracy 49.8 #7 of 36 Archive leaderboard report
Video Question Answering MSRVTT-QA MA-LMM Accuracy 48.5 #5 of 14 Archive leaderboard report
Visual Question Answering (VQA) MSVD-QA MA-LMM Accuracy 0.606 #2 of 36 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

Focus

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