Large language models (LLMs) have achieved remarkable success across diverse applications, yet their generic training paradigm limits effectiveness in user-specific scenarios. LLM personalization aims to adapt large models to individual users or user groups by incorporating preferences, histories, and contextual signal...
Rui-Jie Wang, Qing-Kai Zeng, Xuefei Wang et al.· Proceedings of the 32nd ACM...· 0 citations
PAC-Bayes-regularized Meta-LoRA is proposed, which uses a meta-learned LoRA initialization as both the adaptation start and prior center, while adjusting update strength according to support-set size and predictive uncertainty to limit overfitting under sparse or ambiguous evidence.
Xuefei Wang, Jun Han, Zi-Xuan Wang et al.· 0 citations
These results show that benign execution trajectories can expose proprietary procedural knowledge, and SigLeak, a black-box framework that exploits recurring skill signatures in agent behavior, outperforms or matches three baselines in nearly every setting.
