{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/cat-enhancing-multimodal-large-language-model","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","arxiv_id":"2403.04640","date":"2024-03-07","proceeding":null,"authors":["Qilang Ye","Zitong Yu","Rui Shao","Xinyu Xie","Philip Torr","Xiaochun Cao"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2403.04640v1","url_pdf":"https://arxiv.org/pdf/2403.04640v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"cat-enhancing-multimodal-large-language-model","repo_url":"https://github.com/rikeilong/bay-cat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"audio-visual-question-answering-avqa","task_name":"Audio-Visual Question Answering (AVQA)"},{"task_slug":"audio-visual-question-answering","task_name":"Audio-visual Question Answering"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"multimodal-large-language-model","task_name":"Multimodal Large Language Model"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"video-based-generative-performance","task_name":"Video-based Generative Performance Benchmarking"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-based-generative-performance","task":"Video-based Generative Performance Benchmarking","dataset":"VideoInstruct","model":"CAT-7B","rank_in_archive_order":11,"of":23,"metrics":{"Consistency":"2.89","Contextual Understanding":"3.49","Correctness of Information":"3.08","Detail Orientation":"2.95","Temporal Understanding":"2.81","mean":"3.07"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-activitynet","task":"Zero-Shot Video Question Answer","dataset":"ActivityNet-QA","model":"CAT-7B","rank_in_archive_order":12,"of":28,"metrics":{"Accuracy":"50.2","Confidence Score":"3.5"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-msrvtt-qa","task":"Zero-Shot Video Question Answer","dataset":"MSRVTT-QA","model":"CAT-7B","rank_in_archive_order":11,"of":30,"metrics":{"Accuracy":"62.1","Confidence Score":"3.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.04640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04640"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rikeilong/bay-cat","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_violates":1,"ran_draft_wrong":1,"ran":4,"unverified":6},"by_repo_kind":{"official":{"samples":12,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"rikeilong/bay-cat","repo_kind":"official","path":"ADPO_CAT/model/blip2.py","file_url":"https://github.com/rikeilong/bay-cat/blob/HEAD/ADPO_CAT/model/blip2.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"649fc48067a48529","entry":"find_all_linear_names","repo":"rikeilong/bay-cat","repo_kind":"official","path":"ADPO_CAT/train_dpo.py","file_url":"https://github.com/rikeilong/bay-cat/blob/HEAD/ADPO_CAT/train_dpo.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"649fc48067a48529"}},{"code_sha256_prefix":"3e8496a15d60d4ae","entry":"float2bfloat","repo":"rikeilong/bay-cat","repo_kind":"official","path":"ADPO_CAT/train_dpo.py","file_url":"https://github.com/rikeilong/bay-cat/blob/HEAD/ADPO_CAT/train_dpo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3e8496a15d60d4ae"}},{"code_sha256_prefix":"c3ee9d07c900dd55","entry":"load_image_from_base64","repo":"rikeilong/bay-cat","repo_kind":"official","path":"ADPO_CAT/mm_utils.py","file_url":"https://github.com/rikeilong/bay-cat/blob/HEAD/ADPO_CAT/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c3ee9d07c900dd55"}},{"code_sha256_prefix":"1df990c375318896","entry":"process_images","repo":"rikeilong/bay-cat","repo_kind":"official","path":"ADPO_CAT/mm_utils.py","file_url":"https://github.com/rikeilong/bay-cat/blob/HEAD/ADPO_CAT/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1df990c375318896"}},{"code_sha256_prefix":"cb33571427334815","entry":"tile","repo":"rikeilong/bay-cat","repo_kind":"official","path":"ADPO_CAT/model/base_model.py","file_url":"https://github.com/rikeilong/bay-cat/blob/HEAD/ADPO_CAT/model/base_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cb33571427334815"}},{"code_sha256_prefix":"0ec9fc2025c16f65","entry":"all_gather_with_grad","repo":"rikeilong/bay-cat","repo_kind":"official","path":"ADPO_CAT/model/base_model.py","file_url":"https://github.com/rikeilong/bay-cat/blob/HEAD/ADPO_CAT/model/base_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0ec9fc2025c16f65"}},{"code_sha256_prefix":"d6b600df5a8550bc","entry":"load_lora","repo":"rikeilong/bay-cat","repo_kind":"official","path":"ADPO_CAT/model/builder.py","file_url":"https://github.com/rikeilong/bay-cat/blob/HEAD/ADPO_CAT/model/builder.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d6b600df5a8550bc"}},{"code_sha256_prefix":"875f23fe2e181106","entry":"load_pretrained_model","repo":"rikeilong/bay-cat","repo_kind":"official","path":"ADPO_CAT/model/builder.py","file_url":"https://github.com/rikeilong/bay-cat/blob/HEAD/ADPO_CAT/model/builder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"875f23fe2e181106"}},{"code_sha256_prefix":"616ffbdc154ed2d8","entry":"maybe_zero_3","repo":"rikeilong/bay-cat","repo_kind":"official","path":"ADPO_CAT/train_dpo.py","file_url":"https://github.com/rikeilong/bay-cat/blob/HEAD/ADPO_CAT/train_dpo.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"616ffbdc154ed2d8"}},{"code_sha256_prefix":"37899f22fb191b37","entry":"pretty_print_semaphore","repo":"rikeilong/bay-cat","repo_kind":"official","path":"ADPO_CAT/model/utils.py","file_url":"https://github.com/rikeilong/bay-cat/blob/HEAD/ADPO_CAT/model/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"37899f22fb191b37"}},{"code_sha256_prefix":"f9939a84b9a65279","entry":"violates_moderation","repo":"rikeilong/bay-cat","repo_kind":"official","path":"ADPO_CAT/model/utils.py","file_url":"https://github.com/rikeilong/bay-cat/blob/HEAD/ADPO_CAT/model/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f9939a84b9a65279"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}