{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:33Z","timestamp":1777865313446,"version":"3.51.4"},"reference-count":42,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62495082,U2336205"],"award-info":[{"award-number":["62495082,U2336205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XDB0680202"],"award-info":[{"award-number":["XDB0680202"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00843","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9014-9023","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Multimodal Large Language Models Against Image Corruptions"],"prefix":"10.1109","author":[{"given":"Xinkuan","family":"Qiu","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China,100085"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meina","family":"Kan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongbin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences,Beijing,China,100085"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"imgaug","author":"Jung","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01311"},{"key":"ref3","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3310985"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2437384"},{"key":"ref8","article-title":"How well does gpt-4v (ision) adapt to distribution shifts? a preliminary investigation","volume-title":"ICLR Workshop on Mathematical and Empirical Understanding of Foundation Models","author":"Han","year":"2024"},{"key":"ref9","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"International Conference on Learning Representations","author":"Hendrycks"},{"key":"ref10","author":"Hurst","year":"2024","journal-title":"Gpt-4o system card."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01383-2"},{"key":"ref12","article-title":"Otter: A multi-modal model with in-context instruction tuning","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2025.3558652"},{"key":"ref15","article-title":"A comprehensive survey and guide to multimodal large language models in vision-language tasks","author":"Xin Liang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref17","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02096-6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1080\/01431160600746456"},{"key":"ref22","article-title":"Deepseek-vl: towards real-world vision-language understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref24","article-title":"Robust-llava: On the effectiveness of large-scale robust image encoders for multi-modal large language models","author":"Shadab Malik","year":"2025","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Benchmarking robustness in object detection: Autonomous driving when winter is coming","author":"Michaelis","year":"2019","journal-title":"arXiv preprint"},{"key":"ref26","first-page":"3571","article-title":"On interaction between augmentations and corruptions in natural corruption robustness","author":"Mintun","year":"2021","journal-title":"Advances in Neural Information Processing Systems."},{"key":"ref27","volume-title":"Gpt-4 technical report","author":"Achiam","year":"2024"},{"key":"ref28","article-title":"Benchmarking robustness of multimodal image-text models under distribution shift","author":"Qiu","year":"2023","journal-title":"Journal of Data-centric Machine Learning Research"},{"key":"ref29","article-title":"PCI research and davidlight2018","volume-title":"Transcore-m","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2493"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref32","year":"2025","journal-title":"Qwen2.5-vl"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00540"},{"key":"ref34","article-title":"A comprehensive review of multimodal large language models: Performance and challenges across different tasks","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","volume-title":"The dawn of 1 mms: Preliminary explorations with gpt-4v(ision)","author":"Yang","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref38","article-title":"Lamm: Language-assisted multi-modal instruction-tuning dataset, framework, and benchmark","author":"Yin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","article-title":"Benchmarking large multimodal models against common corruptions","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"On the out-of-distribution generalization of multimodal large language models","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Infmllm: A unified framework for visuallanguage tasks","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","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\/11445632.pdf?arnumber=11445632","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:17Z","timestamp":1777529717000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445632\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00843","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}