An, Kang

2 publications

ICLR 2026 Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs Kang An, Ziliang Wang, Xuhui Zheng, FaQiang Qian, WeiKun Zhang, Yuhang Wang, Yichao Wu

NeurIPS 2025 ASGO: Adaptive Structured Gradient Optimization Kang An, Yuxing Liu, Rui Pan, Yi Ren, Shiqian Ma, Donald Goldfarb, Tong Zhang