{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T12:17:40Z","timestamp":1794917860236,"version":"4.9.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:p>Source-Fully-Free Domain Adaptation (SFF-DA) has emerged as a strategic paradigm to adapt Vision-Language Models (VLMs) without any access to source data or task-specific source models. However, we identify a critical \"Dual Semantic Drift\" that hinders this process: static drift caused by the stagnation of frozen hand-crafted templates, and dynamic drift resulting from noisy, instance-level generated captions. These issues lead to a severe stability-plasticity dilemma, manifesting as semantic misalignment and class collapse.    \nTo address this, we propose DSSG (Dual-Stream Semantic Guidance), an end-to-end framework that reconciles fine-grained plasticity with global stability. Our core contribution is the Dual Semantic Guidance (DSG) module, which integrates a captioning stream for detailed domain nuances with a template stream to anchor global categorical consistency. Furthermore, a Dynamic Cross-Modal Knowledge Distillation (CMKD) module is introduced to adaptively optimize teacher-student alignment across modalities. Extensive experiments demonstrate that DSSG significantly outperforms current state-of-the-art methods across multiple benchmarks, providing a robust solution for the unsupervised transfer of foundation models. The code is available on https:\/\/github.com\/mrmenand\/DSSG.<\/jats:p>","DOI":"10.24963\/ijcai.2026\/211","type":"proceedings-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T22:01:13Z","timestamp":1789596073000},"page":"1893-1901","source":"Crossref","is-referenced-by-count":0,"title":["DSSG: Dual-Stream Semantic Guidance for Source-Fully-Free Adaptation of Vision-Language Models"],"prefix":"10.24963","author":[{"given":"Weiwei","family":"Xiang","sequence":"first","affiliation":[{"name":"Hunan University"},{"name":"Huaihua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shun","family":"Peng","sequence":"additional","affiliation":[{"name":"Hunan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangyi","family":"Xiao","sequence":"additional","affiliation":[{"name":"Hunan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"Hunan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Yang","sequence":"additional","affiliation":[{"name":"Hunan University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10584","event":{"name":"Thirty-Fifth International Joint Conference on Artificial Intelligence {IJCAI-26}","theme":"Artificial Intelligence","location":"Bremen, Germany","acronym":"IJCAI-2026","number":"35","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2026,8,15]]},"end":{"date-parts":[[2026,8,21]]}},"container-title":["Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T11:28:27Z","timestamp":1794914907000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2026\/211"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2026\/211","relation":{},"subject":[],"published":{"date-parts":[[2026,9]]}}}