发表机构
SUSTech; PolyU; CASIA; GDUT; CityU; BigAI; THU; TAU; PKU; UniTrento（南方科技大学; 香港理工大学; 中国科学院自动化研究所; 广东工业大学; 香港城市大学; 北京智源人工智能研究院; 清华大学; 特拉维夫大学; 北京大学; 特伦托大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
LiST是一种无标签测试时LoRA融合框架，通过构建局部单纯形搜索样本特定融合权重，在多模态与语言基准上优于静态LoRA合并及传统测试时自适应方法，提升了未见过任务的鲁棒性。
AI 中文摘要
特定任务的LoRA适配器为大型语言模型与视觉-语言模型提供了一种模块化的专用方式，但现有的适配器组合方法大多是静态的，无法适配单个测试输入。为解决这些问题，我们提出LiST，这是一种无标签的测试时LoRA融合框架，它将现有LoRA库转换为目标条件下的局部单纯形，并在推理时搜索样本特定的融合权重。LiST从LoRA参数锚点和提示级行为向量构建联合任务表示，检索相邻适配器作为局部搜索空间，执行保留分支的融合，且不更新主干或适配器。候选权重由带有先验、几何和随机一致性约束的提示级能量函数选择，仅在通过安全接受规则时才会部署；否则，LiST会回退到目标条件下的先验。在多模态和语言基准上的实验表明，LiST的性能优于静态LoRA合并方法和传统测试时自适应基线，同时保留了特定任务适配器的效用，并提升了在未见过任务上的鲁棒性。
英文摘要
Task-specific LoRA adapters offer a modular way to specialize large language and vision-language models. However, existing adapter composition methods are mostly static and cannot adapt to individual test inputs. To address these issues, we propose \textbf{LiST}, a label-free test-time LoRA fusion framework that converts an existing LoRA bank into a target-conditioned local simplex and searches sample-specific fusion weights at inference time. LiST builds joint task representations from LoRA parameter anchors and prompt-level behavior vectors, retrieves neighboring adapters as a local search space, and performs branch-preserving fusion without updating the backbone or adapters. Candidate weights are selected by a prompt-level energy with prior, geometric, and stochastic-consistency constraints, and are deployed only when they pass a safe acceptance rule. Otherwise, LiST falls back to a target-conditioned prior. Experiments on multimodal and language benchmarks show that LiST outperforms static LoRA merging and conventional test-time adaptation baselines, while preserving task-specific adapter utility and improving robustness on unseen tasks.
CommentsAccepted by EMNLP 2026 Finding
