{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:22:00Z","timestamp":1777890120859,"version":"3.51.4"},"reference-count":47,"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":["No.62472138, No.72188101, No.62020106007"],"award-info":[{"award-number":["No.62472138, No.72188101, No.62020106007"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.00024","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"177-186","source":"Crossref","is-referenced-by-count":0,"title":["SMoLoRa: Exploring and Defying Dual Catastrophic Forgetting in Continual Visual Instruction Tuning"],"prefix":"10.1109","author":[{"given":"Ziqi","family":"Wang","sequence":"first","affiliation":[{"name":"Hefei University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang","family":"Che","sequence":"additional","affiliation":[{"name":"Hefei University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangyang","family":"Li","sequence":"additional","affiliation":[{"name":"Academy of Cyber"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zenglin","family":"Shi","sequence":"additional","affiliation":[{"name":"Hefei University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Openflamingo: An opensource framework for training large autoregressive visionlanguage models","author":"Awadalla","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Continual learning with tiny episodic memories","volume-title":"In Workshop on Multi-Task and Lifelong Reinforcement Learning","author":"Chaudhry","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1844"},{"key":"ref4","article-title":"Mllm-as-a-judge: Assessing multimodal llm-as-a-judge with vision-language benchmark","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"7","key":"ref7","article-title":"Loramoe: Revolutionizing mixture of experts for maintaining world knowledge in language model alignment","volume":"4","author":"Dou","year":"2023","journal-title":"arXiv preprint"},{"issue":"120","key":"ref8","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3678087"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3671616"},{"key":"ref13","article-title":"Multi-modal instruction tuned 11 ms with fine-grained visual perception","author":"He","year":"2024","journal-title":"In CVPR"},{"key":"ref14","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Language is not all you need: Aligning perception with language models","author":"Huang","year":"2023","journal-title":"NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref18","article-title":"Challenges and applications of large language models","author":"Kaddour","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref20","article-title":"Gshard: Scaling giant models with conditional computation and automatic sharding","author":"Lepikhin","year":"2020","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Moe-llava: Mixture of experts for large vision-language models","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref23","article-title":"Moelora: An moe-based parameter efficient fine-tuning method for multitask medical applications","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Dora: Weight-decomposed low-rank adaptation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","author":"Lu","year":"2022","journal-title":"NeurIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref27","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"NeurIPS"},{"key":"ref28","first-page":"2641","article-title":"Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models","author":"A","year":"2015","journal-title":"In ICCV"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref30","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.758"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref35","article-title":"Continual diffusion: Continual customization of text-to-image diffusion with c-lora","author":"Smith","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367329"},{"key":"ref38","article-title":"Exploring the reasoning abilities of multimodal large language models (mllms): A comprehensive survey on emerging trends in multimodal reasoning","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.905"},{"key":"ref40","article-title":"Investigating the catastrophic forgetting in multimodal large language models","author":"Zhai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3777411"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.633"},{"key":"ref43","article-title":"Svit: Scaling up visual instruction tuning","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Beyond anti-forgetting: Multimodal continual instruction tuning with positive forward transfer","author":"Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00319"},{"key":"ref47","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\/11444704.pdf?arnumber=11444704","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:59Z","timestamp":1777613399000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444704\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00024","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}