Yuchuan Wu

Researcher, Alibaba Group

Joined

November 2021

Names

Yuchuan Wu (Preferred)

Emails

****@alibaba-inc.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

Researcher

Alibaba Group (alibaba-inc.com)

2019 – Present

master's degree

Beijing University of Aeronautics and Astronautics (buaa.edu.cn)

2012 – 2015

bachelor's degree

Shandong University (sdu.edu.cn)

2008 – 2012

Advisors, Relations & Conflicts

Coauthor

Yongbin Li

2019 – 2023

Expertise

Conversational AI

Large Language Models

Role Play

2015 – 2024

Publications

EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning
Xiaoqian Liu, Ke Wang, Yongbin Li, Yuchuan Wu, Wentao Ma, Aobo Kong, Fei Huang, Jianbin Jiao, Junge Zhang
- OpenReview Archive Direct Upload
- Readers: Everyone
Reverse Preference Optimization for Complex Instruction Following
Xiang Huang, Ting-En Lin, Feiteng Fang, Yuchuan Wu, Hangyu Li, Yuzhong Qu, Fei Huang, Yongbin Li
- ACL 2025 Findings
- Readers: Everyone
TimeHC-RL: Temporal‑aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence
Guiyang Hou, Gao Xing, Yuchuan Wu, Xiang Huang, Wenqi Zhang, Zhe Zheng, Yongliang Shen, Jialu Du, Fei Huang, Yongbin Li, Weiming Lu
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Agentic Reinforcement Learning with Implicit Step Rewards
Xiaoqian Liu, Ke Wang, Yuchuan Wu, Fei Huang, Yongbin Li, Jianbin Jiao, Junge Zhang
- ICLR 2026 Poster
- Readers: Everyone
P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling
Pinyi Zhang, Ting-En Lin, Yuchuan Wu, Jingyang Chen, Zongqi Wang, Hua Yang, Xu Ze, Fei Huang, Yongbin Li, Kai Zhang
- ICLR 2026 Oral
- Readers: Everyone
MuEdit: A Lightweight yet Effective Multi-task Model Editing Method
Songshi Liang, Ting-En Lin, Zixuan Huang, Yuchuan Wu, Zihe Wang, Yongbin Li, Rui Yan
- Submitted to ICLR 2026
- Readers: Everyone
OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-time Emotional Speech Synthesis
Run Luo, Ting-En Lin, Haonan Zhang, Yuchuan Wu, Xiong Liu, Yongbin Li, Longze Chen, Jiaming Li, Lei Zhang, Xiaobo Xia, Hamid Alinejad-Rokny, Fei Huang, Min Yang
- NeurIPS 2025 poster
- Readers: Everyone
EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning
Xiaoqian Liu, Ke Wang, Yongbin Li, Yuchuan Wu, Wentao Ma, Aobo Kong, Fei Huang, Jianbin Jiao, Jun Zhang
- CoRR 2025
- Readers: Everyone
OpenOmni: Large Language Models Pivot Zero-shot Omnimodal Alignment across Language with Real-time Self-Aware Emotional Speech Synthesis
Run Luo, Ting-En Lin, Haonan Zhang, Yuchuan Wu, Xiong Liu, Min Yang, Yongbin Li, Longze Chen, Jiaming Li, Lei Zhang, Yangyi Chen, Hamid Alinejad-Rokny, Fei Huang
- CoRR 2025
- Readers: Everyone
Diverse AI Feedback For Large Language Model Alignment
Tianshu Yu, Ting-En Lin, Yuchuan Wu, Min Yang, Fei Huang, Yongbin Li
- Trans. Assoc. Comput. Linguistics 2025
- Readers: Everyone

View all 59 publications

Co-Authors

View all 115 co-authors