Author

Xiaoming Zhai

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence May 2026

Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs

A modular, controllable, and efficient framework that selectively relaxes refusal behavior on authorized target domains while preserving standard safety elsewhere, offering a practical path toward foundation models that adapt to diverse professional needs.

Qi-Tao Tan, Xiaoying Song, Arman Akbari et al. · arXiv.org · 1 citation

#artificial intelligence Preprint Sep 2026

Train4Merge: A Controlled Single-Teacher Study of RL vs. SFT Teachers for OPD-Based Model Merging

Domain experts trained from a shared checkpoint can transfer their specialized capabilities to a single student through on-policy distillation (OPD). Existing research primarily focuses on improving this merging process, while the algorithms used to train the experts have received limited systematic comparison. We inve...

Jing-Yuan Huang, Zu-Ming Huang, Yu-Cheng Shi et al. · 0 citations