Yuanshun Yao

Researcher, Meta GenAI

Joined

October 2018

Names

Yuanshun Yao (Preferred)

Kevin Yao

Emails

****@cs.uchicago.edu (Confirmed)

****@bytedance.com (Confirmed)

****@gmail.com (Confirmed)

****@meta.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Researcher

Meta GenAI (meta.com)

2024 – Present

Researcher

ByteDance Research (bytedance.com)

2020 – 2024

PhD student

University of Chicago (cs.uchicago.edu)

2015 – 2020

Advisors, Relations & Conflicts

PhD Advisor

Ben Y. Zhao

Present

PhD Advisor

Haitao Zheng

Present

Expertise

AI Safety

Present

Publications

Beyond Reasoning Gains: Mitigating General Capabilities Forgetting in Large Reasoning Model
Shengjie Bi, Deren Lei, Lijuan Liu, Madian Khabsa, Hoang Phan, Xiaocheng Tang, Xianjun Yang, Yuanshun Yao, Jingyu Zhang
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Label Smoothing Improves Machine Unlearning
Zonglin Di, Zhaowei Zhu, Jinghan Jia, Jiancheng Liu, Zafar Takhirov, Bo Jiang, Yuanshun Yao, Sijia Liu, Yang Liu
- ICLR 2026 Poster
- Readers: Everyone
FEWL: Measuring and Mitigating LLM Hallucination Without Gold-Standard Answers
Jiaheng Wei, Na Di, Yuanshun Yao, Jean-Francois Ton, Hongyi Guo, Andrew Estornell, Yang Liu
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Robust Multi-bit Text Watermark with LLM-based Paraphrasers
Xiaojun Xu, Jinghan Jia, Yuanshun Yao, Yang Liu, Hang Li
- WMARK@ICLR2025
- Readers: Everyone
Learning to watermark LLM-Generated Text Via Reinforcement Learning
Xiaojun Xu, Yuanshun Yao, Yang Liu
- WMARK@ICLR2025
- Readers: Everyone
Robust Multi-bit Text Watermark with LLM-based Paraphrasers
Xiaojun Xu, Jinghan Jia, Yuanshun Yao, Yang Liu, Hang Li
- ICML 2025 poster
- Readers: Everyone
ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration
Andrew Estornell, Jean-Francois Ton, Yuanshun Yao, Yang Liu
- ICLR 2025 Poster
- Readers: Everyone
Human-Instruction-Free LLM Self-Alignment with Limited Samples
Hongyi Guo, Yuanshun Yao, Wei Shen, Jiaheng Wei, Xiaoying Zhang, Zhaoran Wang, Yang Liu
- Submitted to ICLR 2025
- Readers: Everyone
Progressive LLM Alignments Using Two-Player Games
Rui Zheng, Hongyi Guo, Zhihan Liu, Xiaoying Zhang, Yuanshun Yao, Xiaojun Xu, Zhaoran Wang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Yang Liu, Hang Li
- Submitted to ICLR 2025
- Readers: Everyone
Robust RLHF with Noisy Rewards
Wei Shen, Xiaoying Zhang, Yuanshun Yao, Rui Zheng, Hongyi Guo, Yang Liu
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone

View all 45 publications

Co-Authors

View all 72 co-authors