Ziyu Ye

Research Scientist, Google DeepMind

Joined

September 2020

Names

Ziyu Ye (Preferred)

Ziyú Ye

Hazel Ye

Emails

****@uchicago.edu (Confirmed)

****@google.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Homepage

Google Scholar

ORCID

Career & Education History

Research Scientist

Google DeepMind (deepmind.google)

2025 – Present

Student Researcher

Google DeepMind (deepmind.google)

2024 – 2025

PhD student

University of Chicago (uchicago.edu)

2020 – 2025

Research Intern

Google DeepMind (deepmind.google)

2024 – 2024

Advisors, Relations & Conflicts

PhD Advisor

Yuxin Chen

Present

Expertise

reinforcement learning

Present

generative models

Present

Publications

Actor-Curator: Co-adaptive curricula via policy-improvement bandits for post-training
Zhengyao Gu, Jonathan Light, Raul Astudillo, Ziyu Ye, Langzhou He, Wei Cheng, Santiago Paternain, Philip S. Yu, Yisong Yue
- ICLR 2026 Workshop LLM Reasoning Oral
- Readers: Everyone
Actor-Curator: A Scalable RL Post-training Framework with Co-adaptive Curricula
Zhengyao Gu, Jonathan Light, Raul Astudillo, Ziyu Ye, Langzhou He, Wei Cheng, Santiago Paternain, Philip S. Yu, Yisong Yue
- LLA 2026 Poster
- Readers: Everyone
Actor-Curator: Scalable Policy-driven Curriculum Learning for RL Post-Training
Zhengyao Gu, Jonathan Light, Raul Astudillo, Ziyu Ye, Langzhou He, Wei Cheng, Santiago Paternain, Philip S. Yu, Yisong Yue
- ICLR 2026 Workshop RSI Poster
- Readers: Everyone
Actor-curator: A Principled Approach to Online Data Selection for RL Post-training
Zhengyao Gu, Jonathan Light, Raul Astudillo, Ziyu Ye, Langzhou He, Wei Cheng, Santiago Paternain, Philip S. Yu, Yisong Yue
- ICLR 2026 Workshop DATA-FM
- Readers: Everyone
Actor-Curator: Scalable Adaptive Curriculum Learning for LLM Post-Training
Zhengyao Gu, Jonathan Light, Raul Astudillo, Ziyu Ye, Langzhou He, Wei Cheng, Santiago Paternain, Philip S. Yu, Yisong Yue
- SPOT
- Readers: Everyone
When More is Less: Understanding Chain-of-Thought Length in LLMs
Yuyang Wu, Yifei Wang, Ziyu Ye, Tianqi Du, Stefanie Jegelka, Yisen Wang
- ICLR 2026 Poster
- Readers: Everyone
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
Xingyue Huang, Rishabh, Gregor Franke, Ziyi Yang, Jiamu Bai, Weijie Bai, Jinhe Bi, Zifeng Ding, Yiqun Duan, Chengyu Fan, Wendong Fan, Xin Gao, Ruohao Guo, Yuan He, Yicheng He, Xianglong Hu, Neil Johnson, Bowen Li, Fangru Lin, Siyu Lin et al. (26 additional authors not shown)
- LAW
- Readers: Everyone
OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
Mengkang Hu, Yuhang Zhou, Wendong Fan, Yuzhou Nie, Ziyu Ye, Bowei Xia, Tao Sun, Zhaoxuan Jin, Yingru Li, Zeyu Zhang, Yifeng Wang, Qianshuo Ye, Bernard Ghanem, Ping Luo, Guohao Li
- NeurIPS 2025 poster
- Readers: Everyone
Reward-Guided Prompt Evolving in Reinforcement Learning for LLMs
Ziyu Ye, Rishabh Agarwal, Tianqi Liu, Rishabh Joshi, Sarmishta Velury, Quoc V Le, Qijun Tan, Yuan Liu
- ICML 2025 poster
- Readers: Everyone
Evolving Alignment via Asymmetric Self-Play
Ziyu Ye, Rishabh Agarwal, Tianqi Liu, Rishabh Joshi, Sarmishta Velury, Quoc V Le, Qijun Tan, Yuan Liu
- LanGame Spotlight
- Readers: Everyone

View all 19 publications

Co-Authors

View all 94 co-authors