{"ID":2836307,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.21188","arxiv_id":"2511.21188","title":"AnchorOPT: Towards Optimizing Dynamic Anchors for Adaptive Prompt Learning","abstract":"Existing prompt learning methods, which are built upon CLIP models, leverage textual tokens as anchors to guide the learnable soft tokens. This guidance improves CLIP generalizations. However, these anchors-static in both value and position-lack cross-task and stage-adaptive flexibility. To address this limitation, we propose AnchorOPT, a dynamic anchor-based prompt learning framework. Specifically, AnchorOPT introduces dynamism in two key dimensions: (i) anchor values eschew handcrafted explicit textual tokens (e.g., \"shape\", \"color\"), instead learning dynamically from task-specific data; and (ii) the positional relationship between anchor and soft tokens is no longer fixed but adaptively optimized via a learnable position matrix conditioned on the training stage and task context. Training occurs in two stages: we first learn the anchor tokens, then freeze and transfer them to the second stage for optimization of soft tokens and the position matrix. Extensive experiments demonstrate that using only a simple learnable anchor and position matrix achieves performance comparable to or exceeding some methods incorporating additional learnable modules or regularization techniques. As a plug-and-play module, AnchorOPT integrates seamlessly into existing frameworks, yielding consistent performance gains across diverse datasets. Code is publicly available at https://github.com/zhengli97/ATPrompt.","short_abstract":"Existing prompt learning methods, which are built upon CLIP models, leverage textual tokens as anchors to guide the learnable soft tokens. This guidance improves CLIP generalizations. However, these anchors-static in both value and position-lack cross-task and stage-adaptive flexibility. To address this limitation, we...","url_abs":"https://arxiv.org/abs/2511.21188","url_pdf":"https://arxiv.org/pdf/2511.21188v1","authors":"[\"Zheng Li\",\"Yibing Song\",\"Xin Zhang\",\"Lei Luo\",\"Xiang Li\",\"Jian Yang\"]","published":"2025-11-26T09:11:22Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.CL\"]","methods":"[]","has_code":false,"code_links":[{"ID":606588,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2836307,"paper_url":"https://arxiv.org/abs/2511.21188","paper_title":"AnchorOPT: Towards Optimizing Dynamic Anchors for Adaptive Prompt Learning","repo_url":"https://github.com/zhengli97/ATPrompt","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}