{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T06:09:05Z","timestamp":1783490945105,"version":"3.55.0"},"reference-count":87,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00156","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1590-1601","source":"Crossref","is-referenced-by-count":1,"title":["AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs"],"prefix":"10.1109","author":[{"given":"Sanjoy","family":"Chowdhury","sequence":"first","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sayan","family":"Nag","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subhrajyoti","family":"Dasgupta","sequence":"additional","affiliation":[{"name":"Mila and Universite de Montreal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaoting","family":"Wang","sequence":"additional","affiliation":[{"name":"KAUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed","family":"Elhoseiny","sequence":"additional","affiliation":[{"name":"KAUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruohan","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Openflamingo: An opensource framework for training large autoregressive visionlanguage models","author":"Awadalla","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"X-llm: Bootstrapping advanced large language models by treating multi-modalities as foreign languages","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3185"},{"key":"ref8","article-title":"Videollama 2: Advancing spatialtemporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02533"},{"issue":"70","key":"ref12","first-page":"1","article-title":"Scaling instructionfinetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","article-title":"Think you have solved question answering? try arc, the ai2 reasoning challenge","author":"Clark","year":"2018","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref15","article-title":"Enhancing large vision language models with self-training on image comprehension","author":"Deng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1214\/20-AOS2004"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref19","author":"Gong","year":"2024","journal-title":"Av-odyssey bench: Can your multimodal 11 ms really understand audio-visual information?"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02510"},{"key":"ref21","article-title":"Imagebind-llm: Multi-modality instruction tuning","author":"Han","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Measuring massive multitask language understanding","author":"Hendrycks","year":"2020","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"International conference on machine learning","author":"Jaegle","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"ref25","article-title":"Fgaif: Aligning large visionlanguage models with fine-grained ai feedback","author":"Jing","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Seed-bench: Benchmarking multimodal 11 ms with generative comprehension","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3571946"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"ref29","article-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02095"},{"key":"ref32","article-title":"Silkie: Preference distillation for large visual language models","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Silkie: Preference distillation for large visual language models","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref35","author":"Li","year":"2024","journal-title":"Omnibench: Towards the future of universal omni-language models"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref37","article-title":"Hallusionbench: You see what you think? or you think what you see? an image-context reasoning benchmark challenging for gpt-4v (ision), llava-1.5, and other multi-modality models","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref39","author":"Liu","year":"2024","journal-title":"Statistical rejection sampling improves preference optimization"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref41","article-title":"Unified-io: A unified model for vision, language, and multi-modal tasks","author":"Lu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02497"},{"key":"ref43","article-title":"Valley: Video assistant with large language model enhanced ability","author":"Luo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Macaw-llm: Multi-modal language modeling with image, audio, video, and text integration","author":"Lyu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref46","article-title":"Video-bench: A comprehensive benchmark and toolkit for evaluating video-based large language models","author":"Ning","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","volume-title":"Hello gpt-4","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref49","article-title":"X-instructblip: A framework for aligning x -modal instruction-aware representations to 11 ms and emergent cross-modal reasoning","author":"Panagopoulou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_22"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01335"},{"key":"ref53","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref54","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Reid","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01357"},{"key":"ref56","article-title":"Mitigating object hallucination via data augmented contrastive tuning","author":"Sarkar","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Pandagpt: One model to instruction-follow them all","author":"Su","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"video-salmonn: Speech-enhanced audio-visual large language models","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Aligning large multimodal models with factually augmented rlhf","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref60","author":"Sung-Bin","year":"2024","journal-title":"Avhbench: A cross-modal hallucination benchmark for audio-visual large language models"},{"key":"ref61","volume-title":"Stanford alpaca: An instruction-following llama model","author":"Taori","year":"2023"},{"key":"ref62","article-title":"Reka core, flash, and edge: A series of powerful multimodal language models","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00517"},{"key":"ref64","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref65","volume-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref66","article-title":"What makes for good visual tokenizers for large language models?","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34744"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3507000"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548291"},{"key":"ref71","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref72","article-title":"Cat: enhancing multimodal large language model to answer questions in dynamic audio-visual scenarios","author":"Ye","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref74","article-title":"Lamm: Language-assisted multi-modal instruction-tuning dataset, framework, and benchmark","volume":"36","author":"Yin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01310"},{"key":"ref76","article-title":"Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref77","article-title":"Mm-vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref78","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.521"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref82","article-title":"Llamaadapter: Efficient fine-tuning of language models with zeroinit attention","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_4"},{"key":"ref84","article-title":"Chatbridge: Bridging modalities with large language model as a language catalyst","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref85","article-title":"Beyond hallucinations: Enhancing lvlms through hallucination-aware direct preference optimization","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref86","article-title":"Aligning modalities in vision large language models via preference fine-tuning","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref87","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446102.pdf?arnumber=11446102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:33:23Z","timestamp":1777613603000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446102\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":87,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00156","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}