{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:36:34Z","timestamp":1761176194536,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>Deep Neural Networks suffer significant performance degradation when faced with distribution shifts between training and test data. Test-time adaptation (TTA) has emerged as a practical solution that enables models to adapt to the shifted test distribution. Currently, most existing TTA methods are designed around a single model, which incorporate limited information from a singular data distribution. In practice, pre-trained models derived from diverse source domains are readily accessible, each capturing a distinct data distribution and containing complementary information. To exploit this diversity, we propose Model Fusion-based multi-source Test-Time Adaptation (MFTTA), which constructs a target model by fusing the parameters of multiple source models. Drawing inspiration from deep model fusion, we introduce a fine-grained fusion mechanism governed by an off-policy reinforcement learning agent, which dynamically assigns fusion weights based on the current data distribution. Furthermore, we design a correlation-aware model update strategy that prioritizes the source model most relevant to the incoming test data. Extensive experiments on standard out-of-distribution benchmarks demonstrate that our method effectively integrates knowledge from multiple source models, adapts robustly to dynamic distribution shifts, and alleviates the problem of forgetting in long-term adaptation.<\/jats:p>","DOI":"10.3233\/faia251064","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:50:23Z","timestamp":1761126623000},"source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Model Fusion for Multi-Source Test-Time Adaptation"],"prefix":"10.3233","author":[{"given":"Yuan","family":"Xue","sequence":"first","affiliation":[{"name":"Tsinghua University"}]},{"given":"Qinting","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Yuan","family":"Meng","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Xingxuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Chen","family":"Tang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Jingyan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University"}]},{"given":"Zhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA251064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:50:24Z","timestamp":1761126624000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA251064"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia251064","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}