{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:22:34Z","timestamp":1791912154558,"version":"4.3.4"},"reference-count":48,"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\/iccv51701.2025.00020","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"133-143","source":"Crossref","is-referenced-by-count":4,"title":["Latte: Collaborative Test-Time Adaptation of Vision-Language Models in Federated Learning"],"prefix":"10.1109","author":[{"given":"Wenxuan","family":"Bao","sequence":"first","affiliation":[{"name":"University of Illinois Urbana-Champaign"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruxi","family":"Deng","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruizhong","family":"Qiu","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianxin","family":"Wei","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanghang","family":"Tong","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingrui","family":"He","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"547","article-title":"A simple zero-shot prompt weighting technique to improve prompt ensembling in text-image models","author":"Allingham","year":"2023","journal-title":"ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3403"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3906"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91672-4_8"},{"key":"ref6","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2013.208"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4099"},{"key":"ref9","first-page":"2704","article-title":"Diverse data augmentation with diffusions","author":"Feng","year":"2023","journal-title":"ICCV"},{"key":"ref10","article-title":"In search of lost domain generalization","author":"Gulrajani","year":"2021","journal-title":"ICLR"},{"key":"ref11","first-page":"1364","article-title":"pfedprompt: Learning personalized prompt","author":"Guo","year":"2023","journal-title":"WWW"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3302410"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","article-title":"Benchmarking neural network robustness","author":"Hendrycks","year":"2019","journal-title":"ICLR"},{"key":"ref15","article-title":"AugMix","author":"Hendrycks","year":"2020","journal-title":"ICLR"},{"key":"ref16","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref17","article-title":"Test-time robust personalization for federated learning","author":"Jiang","year":"2023","journal-title":"ICLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837896"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01343"},{"key":"ref20","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref21","first-page":"1","article-title":"A comprehensive survey on test-time adaptation under distribution shifts","author":"Liang","year":"2024","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"ref22","first-page":"52","article-title":"Fedclip: Fast generalization and personalization for CLIP in federated learning","volume":"46","author":"Lu","year":"2023","journal-title":"IEEE Data Engineering Bulletin"},{"key":"ref23","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017","journal-title":"Proceedings of AISTATS"},{"key":"ref24","article-title":"Federated learning from vision-language foundation models: Theoretical analysis and method","author":"Pan","year":"2024","journal-title":"NeurIPS"},{"key":"ref25","article-title":"Federated text-driven prompt generation for vision-language models","author":"Qiu","year":"2024","journal-title":"ICLR"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref27","article-title":"Align your prompts: Test-time prompting with distribution alignment","author":"Samadh","year":"2023","journal-title":"NeurIPS"},{"key":"ref28","first-page":"8469","article-title":"The impact of neural network overparameterization on gradient confusion","volume-title":"ICML","author":"Sankararaman","year":"2020"},{"key":"ref29","article-title":"Test-time prompt tuning for zero-shot generalization","author":"Shu","year":"2022","journal-title":"NeurIPS"},{"key":"ref30","first-page":"825","article-title":"Test-time prototype shifting for zero-shot generalization","author":"Sui","year":"2025","journal-title":"WACV"},{"key":"ref31","article-title":"Taming heterogeneity in federated learning","author":"Tan","year":"2023","journal-title":"NeurIPS"},{"key":"ref32","first-page":"2579","article-title":"Visualizing data using t-SNE","author":"van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref33","article-title":"Tent: Fully test-time adaptation by entropy minimization","author":"Wang","year":"2021","journal-title":"ICLR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2307\/2304460"},{"key":"ref35","article-title":"Beyond model adaptation at test time: A survey","author":"Xiao","year":"2024","journal-title":"CoRR"},{"key":"ref36","first-page":"4370","article-title":"A joint training-calibration framework","author":"Xu","year":"2023","journal-title":"CIKM"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.595"},{"key":"ref38","article-title":"Dual prototype evolving for test-time generalization of vision-language models","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Zhang","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29611"},{"key":"ref40","article-title":"Historical test-time prompt tuning for vision foundation models","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Zhang","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671908"},{"key":"ref42","article-title":"MEMO: Test-time robustness via adaptation","author":"Zhang","year":"2022","journal-title":"NeurIPS"},{"key":"ref43","first-page":"493","article-title":"Tip-adapter: Training-free adaptation of CLIP","author":"Zhang","year":"2022","journal-title":"ECCV"},{"key":"ref44","article-title":"Boostadapter: Improving vision-language adaptation","author":"Zhang","year":"2024","journal-title":"NeurIPS"},{"key":"ref45","first-page":"41647","article-title":"Adanpc: Non-parametric classifier for test-time adaptation","author":"Zhang","year":"2023","journal-title":"ICML"},{"key":"ref46","first-page":"28718","article-title":"Dual memory networks for vision-language models","author":"Zhang","year":"2024","journal-title":"CVPR"},{"key":"ref47","first-page":"16795","article-title":"Conditional prompt learning","author":"Zhou","year":"2022","journal-title":"CVPR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"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\/11444537.pdf?arnumber=11444537","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:52:44Z","timestamp":1777611164000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444537\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00020","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}