{"ID":2874270,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.10535","arxiv_id":"2509.10535","title":"Semantic-guided LoRA Parameters Generation","abstract":"Low-Rank Adaptation (LoRA) has demonstrated strong generalization capabilities across a variety of tasks for efficiently fine-tuning AI models, especially on resource-constrained edges. However, in real-world applications, edge users often exhibit task-specific preferences that are difficult to handle with a unified model trained under a closed-world assumption, and the challenge may further increase when there are significant domain shifts between training and deployment. Meanwhile, retraining/fine-tuning models for each user is also impractical due to its cost-intensive nature and privacy concerns over raw data utilization from edges. To address these challenges, we propose Semantic-guided LoRA Parameter Generation (SG-LoRA), the first of its kind framework to efficiently produce user-specific LoRA parameters without any additional training on user tasks or access to user-specific data. Concretely, SG-LoRA uses task descriptions as the semantic bridge, measuring their proximity to a set of known expert tasks in a shared embedding space. Based on this semantic guidance, it models the target task's LoRA parameter distribution to generate high-performing parameters for novel tasks. SG-LoRA enables the real-time construction of LoRA models aligned with individual intents by distilling knowledge from prominent LoRA experts and, meanwhile, offering a privacy-preserving solution for personalized model adaptation in a novel zero-shot open-world setting proposed in this work. Extensive experiments on multiple challenging tasks confirm the superior performance and remarkable adaptability of SG-LoRA. Code is available at https://github.com/keepgoingjkg/SG-LoRA.","short_abstract":"Low-Rank Adaptation (LoRA) has demonstrated strong generalization capabilities across a variety of tasks for efficiently fine-tuning AI models, especially on resource-constrained edges. However, in real-world applications, edge users often exhibit task-specific preferences that are difficult to handle with a unified mo...","url_abs":"https://arxiv.org/abs/2509.10535","url_pdf":"https://arxiv.org/pdf/2509.10535v1","authors":"[\"Miaoge Li\",\"Yang Chen\",\"Zhijie Rao\",\"Can Jiang\",\"Jingcai Guo\"]","published":"2025-09-05T14:43:41Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"LoRA\"]","has_code":false,"code_links":[{"ID":610126,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2874270,"paper_url":"https://arxiv.org/abs/2509.10535","paper_title":"Semantic-guided LoRA Parameters Generation","repo_url":"https://github.com/keepgoingjkg/SG-LoRA","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}