Papers › Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time

Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time

1 Jul 2024arXiv:2407.01851archive 2025-07-28

Sanjoy Chowdhury, Sayan Nag, Subhrajyoti Dasgupta, Jun Chen, Mohamed Elhoseiny, Ruohan Gao, Dinesh Manocha

Leveraging Large Language Models' remarkable proficiency in text-based tasks, recent works on Multi-modal LLMs (MLLMs) extend them to other modalities like vision and audio. However, the progress in these directions has been mostly focused on tasks that only require a coarse-grained understanding of the audio-visual semantics. We present Meerkat, an audio-visual LLM equipped with a fine-grained understanding of image and audio both spatially and temporally. With a new modality alignment module based on optimal transport and a cross-attention module that enforces audio-visual consistency, Meerkat can tackle challenging tasks such as audio referred image grounding, image guided audio temporal localization, and audio-visual fact-checking. Moreover, we carefully curate a large dataset AVFIT that comprises 3M instruction tuning samples collected from open-source datasets, and introduce MeerkatBench that unifies five challenging audio-visual tasks. We achieve state-of-the-art performance on all these downstream tasks with a relative improvement of up to 37.12%.

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="2407.01851")

Code

Syntology Ran 8 of 12 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 6 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

schowdhury671/meerkat 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

12 samples harvested; 8 ran; 0 honoured the contract we drafted; 4 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 · our draft was wrong
1ran · fixture could not drive it
6ran
4unverified

Licence: 0 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 schowdhury671/meerkat. “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.

IPOT_distance_torch schowdhury671/meerkat/ot.py official repository ran Apache-2.0 (permissive) · 2e29aff3235aa10d · report
IPOT_torch schowdhury671/meerkat/ot.py official repository ran Apache-2.0 (permissive) · b5722793bedbd27d · report
apply_rotary_pos_emb schowdhury671/meerkat/modeling.py official repository ran Apache-2.0 (permissive) · c5acd613a38384de · report
cost_matrix_torch schowdhury671/meerkat/ot.py official repository ran fingerprinted Apache-2.0 (permissive) · d79fd2ac61421292 · report
create_positional_encoding schowdhury671/meerkat/modeling.py official repository ran fingerprinted Apache-2.0 (permissive) · cd8d3c38c1c00782 · report
draw_samples schowdhury671/meerkat/llm_trainer.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 85940fcc885772a0 · report
prepare_model_for_training schowdhury671/meerkat/run_clm_llms.py official repository ran Apache-2.0 (permissive) · 41e656ac2d002178 · report
rotate_half schowdhury671/meerkat/modeling.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · e03d53ba9d4f9ae5 · report
load_datasets schowdhury671/meerkat/run_clm_llms.py official repository unverified Apache-2.0 (permissive) · 14a47047d9a6be42 · report
load_datasets schowdhury671/meerkat/run_clm_llms_inference.py official repository unverified Apache-2.0 (permissive) · 5a4fa70c9f9c5fb7 · report
preprocess_alpaca_to_tensor_dataset schowdhury671/meerkat/preprocess_data_supervised.py official repository unverified Apache-2.0 (permissive) · 219ec7b58f19dfd1 · report
preprocess_vqa2_to_tensor_dataset schowdhury671/meerkat/preprocess_data_supervised.py official repository unverified Apache-2.0 (permissive) · 042def84c77ef6b4 · report

Tasks

AUDIO-VISUAL QUESTION ANSWERING (MUSIC-AVQA-v2.0)Fact CheckingLanguage ModelingLanguage ModellingLarge Language ModelTemporal Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
AUDIO-VISUAL QUESTION ANSWERING (MUSIC-AVQA-v2.0) MUSIC-AVQA v2.0 Meerkat Accuracy 79.15 #1 of 5 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

Concatenated Skip ConnectionSoftmax

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