Liyuan Mao

PhD student, Shanghai Jiaotong University

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Information-Theoretic Reward Decomposition for Generalizable RLHF

#311 · Liyuan Mao, Haoran Xu, Amy Zhang, Weinan Zhang, Chenjia Bai

In this paper, we decompose the reward value into prompt-free reward and prompt-related reward from a information-theoretic perspective, and use the former to guide reward training.

Poster Session 3

1 paper

Thursday, December 4, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Uni-RL: Unifying Online and Offline RL via Implicit Value Regularization

#303 · Haoran Xu, Liyuan Mao, Hui Jin, Weinan Zhang, Xianyuan Zhan, Amy Zhang

A unified and scalable RL framework applicable to online, offline, and offline-to-online settings.