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 conver...
Yi-Hua Shao, Jia Li, Si-Yu Chen et al.· 2 citations
D-Loop is proposed, which introduces \emph{intra-block causal conditioning} within the original diffusion drafter without additional model components, and can beat DFlash and DSpark on Qwen3-4B and Qwen3-8B with obvious gains.
Ke-Cheng Chen, Yu-Yang He, Cheng Gong et al.· 0 citations
This work identifies two distinct requirements for successful editing: covering every required change and placing precise boundaries around it, and shows why strong infilling capability alone does not ensure reliable editing.
Xi-Jia Tao, Zi-Rui Liu, Shansan Gong et al.· arXiv.org· 0 citations
Findings show that a skill document can serve as the starting point for a continuous control that improves both answers and actions without updating the backbone.
Xi-Jia Tao, Yi-Hua Teng, Xin-Yu Fu et al.· arXiv.org· 3 citations
RedEvoAgent is proposed, a black-box red-teaming agent that distills cross-case attack trajectories into a concise, human-readable attack skill that outperforms fixed and agentic baselines, improves tool efficiency, and transfers across attacker models and target execution harnesses.
Jun-Jie Zhang, Hui Liu, Ke-Cheng Chen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.