{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:27Z","timestamp":1777865367266,"version":"3.51.4"},"reference-count":63,"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\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0116500"],"award-info":[{"award-number":["2022ZD0116500"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222609,62320106010"],"award-info":[{"award-number":["62222609,62320106010"]}],"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\/iccv51701.2025.00131","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1325-1335","source":"Crossref","is-referenced-by-count":0,"title":["Federated Continual Instruction Tuning"],"prefix":"10.1109","author":[{"given":"Haiyang","family":"Guo","sequence":"first","affiliation":[{"name":"School of Advanced Interdisciplinary Sciences,UCAS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fanhu","family":"Zeng","sequence":"additional","affiliation":[{"name":"MAIS, CASIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Zhu","sequence":"additional","affiliation":[{"name":"Centre for Artificial Intelligence and Robotics, HKISI-CAS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenzhuo","family":"Liu","sequence":"additional","affiliation":[{"name":"MAIS, CASIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Da-Han","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer and Information Engineering, Xiamen University of Technology,FKLPRIU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Xu","sequence":"additional","affiliation":[{"name":"MAIS, CASIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu-Yao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Advanced Interdisciplinary Sciences,UCAS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng-Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Advanced Interdisciplinary Sciences,UCAS"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A data-free approach to mitigate catastrophic forgetting in federated class incremental learning for vision tasks","author":"Babakniya","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref2","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","article-title":"Continual llava: Continual instruction tuning in large vision-language models","author":"Cao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1844"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.29007"},{"key":"ref8","article-title":"Clevr-math: A dataset for compositional language, visual and mathematical reasoning","volume-title":"In 16th International Workshop on Neural-Symbolic Learning and Reasoning","author":"Lindstr\u00f6m","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00992"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73650-6_9"},{"key":"ref13","article-title":"Desire: Dynamic knowledge consolidation for rehearsal-free continual learning","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.666"},{"key":"ref15","article-title":"A comprehensive survey on continual learning in generative models","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref17","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Harry Hsu","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Lora: Low-rank adaptation of large language models","author":"Edward","year":"2021","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01565"},{"key":"ref20","article-title":"Mistral 7b","author":"Albert","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref22","article-title":"Fig-ureqa: An annotated figure dataset for visual reasoning","author":"Ebrahimi Kahou","year":"2017","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"1687716896. PMLR","article-title":"Learnability and algorithm for continual learning","volume-title":"International Conference on Machine Learning","author":"Kim","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref25","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.775"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00077"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01437"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1398-0"},{"key":"ref32","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems, 36"},{"key":"ref33","article-title":"Llava-c: Continual improved visual instruction tuning","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Iconqa: A new benchmark for abstract diagram understanding and visual language reasoning","volume-title":"The 35th Conference on Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks","author":"Lu","year":"2021"},{"key":"ref36","article-title":"Dynamic prompt learning via policy gradient for semi-structured mathematical reasoning","author":"Lu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref38","first-page":"1273","article-title":"Communicationefficient learning of deep networks from decentralized data","author":"McMahan","year":"2017","journal-title":"Artificial intelligence and statistics"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref42","article-title":"Adaptive federated optimization","author":"Reddi","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"The future of large language model pre-training is federated","author":"Sani","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00534"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-024-1502-8"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20819"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1405"},{"key":"ref49","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.715"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref52","article-title":"Flora: Federated finetuning large language models with heterogeneous low-rank adaptations","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.450"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3363240"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671582"},{"key":"ref56","article-title":"Modalprompt: Dual-modality guided prompt for continual learning of large multimodal models","author":"Zeng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00441"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447454"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2989782"},{"key":"ref60","article-title":"Mllm-cl: Continual learning for multimodal large language models","author":"Zhao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00581"},{"key":"ref63","article-title":"Open-world machine learning: A review and new outlooks","author":"Zhu","year":"2024","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\/11444222.pdf?arnumber=11444222","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:21:38Z","timestamp":1777530098000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444222\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00131","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}