NeurIPS

Robust Federated Finetuning of LLMs via Alternating Optimization of LoRA

Shuangyi Chen, Yuanxin Guo, Yue Ju, Harik Dalal, Zhongwen Zhu, Ashish Khisti

机构 * University of Toronto（多伦多大学） ； Ericsson-GAIA Montréal（爱立信-GAIA蒙特利尔） 纠错

Comments Accepted to NeurIPS 2025

Journal ref https://openreview.net/forum?id=e8DrPuJekZ&referrer=%5BAuthor%20Console%5D(%2Fgroup%3Fid%3DNeurIPS.cc%2F2025%2FConference%2FAuthors%23your-submissions)

A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation

Yiwen Tu, Pingbang Hu, Jiaqi Ma

机构 * University of Michigan, Ann Arbor（密歇根大学安阿伯分校） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

Comments Accepted at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)