Papers › CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic...

CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios

7 Mar 2024arXiv:2403.04640archive 2025-07-28

Qilang Ye, Zitong Yu, Rui Shao, Xinyu Xie, Philip Torr, Xiaochun Cao

This paper focuses on the challenge of answering questions in scenarios that are composed of rich and complex dynamic audio-visual components. Although existing Multimodal Large Language Models (MLLMs) can respond to audio-visual content, these responses are sometimes ambiguous and fail to describe specific audio-visual events. To overcome this limitation, we introduce the CAT, which enhances MLLM in three ways: 1) besides straightforwardly bridging audio and video, we design a clue aggregator that aggregates question-related clues in dynamic audio-visual scenarios to enrich the detailed knowledge required for large language models. 2) CAT is trained on a mixed multimodal dataset, allowing direct application in audio-visual scenarios. Notably, we collect an audio-visual joint instruction dataset named AVinstruct, to further enhance the capacity of CAT to model cross-semantic correlations. 3) we propose AI-assisted ambiguity-aware direct preference optimization, a strategy specialized in retraining the model to favor the non-ambiguity response and improve the ability to localize specific audio-visual objects. Extensive experimental results demonstrate that CAT outperforms existing methods on multimodal tasks, especially in Audio-Visual Question Answering (AVQA) tasks. The codes and the collected instructions are released at https://github.com/rikeilong/Bay-CAT.

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="2403.04640")

Code

Syntology Ran 6 of 12 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · our draft was wrong; 4 ran with no contract checked.

By repository: official repository: 12 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.

rikeilong/bay-cat 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; 6 ran; 0 honoured the contract we drafted; 6 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 · violated contract
1ran · our draft was wrong
4ran
6unverified

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 rikeilong/bay-cat. “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.

disabled_train rikeilong/bay-cat/ADPO_CAT/model/blip2.py official repository ran · violated contract Apache-2.0 (permissive) · 4cb732f513d69dfd · report
find_all_linear_names rikeilong/bay-cat/ADPO_CAT/train_dpo.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 649fc48067a48529 · report
float2bfloat rikeilong/bay-cat/ADPO_CAT/train_dpo.py official repository ran Apache-2.0 (permissive) · 3e8496a15d60d4ae · report
load_image_from_base64 rikeilong/bay-cat/ADPO_CAT/mm_utils.py official repository ran Apache-2.0 (permissive) · c3ee9d07c900dd55 · report
process_images rikeilong/bay-cat/ADPO_CAT/mm_utils.py official repository ran Apache-2.0 (permissive) · 1df990c375318896 · report
tile rikeilong/bay-cat/ADPO_CAT/model/base_model.py official repository ran fingerprinted Apache-2.0 (permissive) · cb33571427334815 · report
all_gather_with_grad rikeilong/bay-cat/ADPO_CAT/model/base_model.py official repository unverified Apache-2.0 (permissive) · 0ec9fc2025c16f65 · report
load_lora rikeilong/bay-cat/ADPO_CAT/model/builder.py official repository unverified Apache-2.0 (permissive) · d6b600df5a8550bc · report
load_pretrained_model rikeilong/bay-cat/ADPO_CAT/model/builder.py official repository unverified Apache-2.0 (permissive) · 875f23fe2e181106 · report
maybe_zero_3 rikeilong/bay-cat/ADPO_CAT/train_dpo.py official repository unverified Apache-2.0 (permissive) · 616ffbdc154ed2d8 · report
pretty_print_semaphore rikeilong/bay-cat/ADPO_CAT/model/utils.py official repository unverified Apache-2.0 (permissive) · 37899f22fb191b37 · report
violates_moderation rikeilong/bay-cat/ADPO_CAT/model/utils.py official repository unverified Apache-2.0 (permissive) · f9939a84b9a65279 · report

Tasks

Audio-Visual Question Answering (AVQA)Audio-visual Question AnsweringLanguage ModelingLanguage ModellingLarge Language ModelMultimodal Large Language ModelQuestion AnsweringVideo-based Generative Performance BenchmarkingVisual Question AnsweringZero-Shot Video Question Answer

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video-based Generative Performance Benchmarking VideoInstruct CAT-7B Consistency 2.89 #11 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct CAT-7B Contextual Understanding 3.49 #11 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct CAT-7B Correctness of Information 3.08 #11 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct CAT-7B Detail Orientation 2.95 #11 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct CAT-7B Temporal Understanding 2.81 #11 of 23 Archive leaderboard report
Video-based Generative Performance Benchmarking VideoInstruct CAT-7B mean 3.07 #11 of 23 Archive leaderboard report
Zero-Shot Video Question Answer ActivityNet-QA CAT-7B Accuracy 50.2 #12 of 28 Archive leaderboard report
Zero-Shot Video Question Answer ActivityNet-QA CAT-7B Confidence Score 3.5 #12 of 28 Archive leaderboard report
Zero-Shot Video Question Answer MSRVTT-QA CAT-7B Accuracy 62.1 #11 of 30 Archive leaderboard report
Zero-Shot Video Question Answer MSRVTT-QA CAT-7B Confidence Score 3.5 #11 of 30 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