{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:31:40Z","timestamp":1770845500476,"version":"3.50.1"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007957","name":"Chongqing Municipal Education Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007957","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11343481","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"6325-6330","source":"Crossref","is-referenced-by-count":0,"title":["Revisiting Multi-Modal Alignment: In Distribution View"],"prefix":"10.1109","author":[{"given":"Weikai","family":"Li","sequence":"first","affiliation":[{"name":"Chongqing Jiaotong University,School of Mathematics and Statistics,Chongqing,China,400074"}]},{"given":"Nan","family":"Tian","sequence":"additional","affiliation":[{"name":"Chongqing Jiaotong University,School of Mathematics and Statistics,Chongqing,China,400074"}]},{"given":"Yuan","family":"Li","sequence":"additional","affiliation":[{"name":"China Science IntelliCloud Technology, Co., Ltd.,Anhui,China,230000"}]},{"given":"Ying","family":"Tang","sequence":"additional","affiliation":[{"name":"Rowan University,Department of Electrical and Computer Engineering,Glassboro,NJ,USA,08028"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref3","article-title":"3d-ct-gpt: Generating 3d radiology reports through integration of large vision-language models","author":"Chen","year":"2024"},{"key":"ref4","article-title":"Vinci. r1-v: Reinforcing super generalization ability in vision-language models with less than 3","author":"Chen"},{"key":"ref5","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","article-title":"Fine-tuning clip\u2019s last visual projector: A few-shot cornucopia","author":"Fahes","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref10","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref12","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"issue":"2","key":"ref15","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref16","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02553"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02319"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref23","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02327"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref28","article-title":"Mia-dpo: Multi-image augmented direct preference optimization for large vision-language models","author":"Liu","year":"2024"},{"key":"ref29","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref31","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref34","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_35"},{"key":"ref36","article-title":"Enhancing multimodal llm for detailed and accurate video captioning using multi-round preference optimization","author":"Tang","year":"2024"},{"key":"ref37","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref38","article-title":"Actionclip: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02779"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0480"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02008"},{"key":"ref42","article-title":"Next-gpt: Any-to-any multimodal llm","volume-title":"Forty-first International Conference on Machine Learning","author":"Wu"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02212"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3347693"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref47","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11343481.pdf?arnumber=11343481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:50:55Z","timestamp":1770843055000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11343481\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11343481","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}