Publications

(For the most up-to-date publications, please visit my Google Scholar.)

Zichen Liu^*, Anya Sims^*, Keyu Duan^*, Changyu Chen^*, Simon Yu, Xiangxin Zhou, Haotian Xu, Shaopan Xiong, Bo Liu, Chenmien Tan, Weixun Wang, Hao Zhu, Weiyan Shi, Diyi Yang, Michael Qizhe Shieh, Yee Whye Teh, Wee Sun Lee, Min Lin
GEM: A Gym for Generalist LLMs
Proceedings of ICLR, 2026 [pdf] [code]
SEA Workshop @ NeurIPS, 2025 (Outstanding Paper)

Keyu Duan, Zichen Liu, Xin Mao, Tianyu Pang, Changyu Chen, Qiguang Chen, Michael Qizhe Shieh, Longxu Dou
Efficient Process Reward Model Training via Active Learning
Proceedings of COLM, 2025 [pdf] [code] [data] [model]

Zichen Liu^*, Changyu Chen^*, Wenjun Li^*, Penghui Qi^*, Tianyu Pang, Chao Du, Wee Sun Lee, Min Lin
Understanding R1-Zero-Like Training: A Critical Perspective
Proceedings of COLM, 2025 (Oral) [pdf] [code]
AI4MATH Workshop @ ICML, 2025 (Best Paper Runner-Up)

Changyu Chen^*, Zichen Liu^*, Chao Du^†, Tianyu Pang, Qian Liu, Arunesh Sinha^†, Pradeep Varakantham^†, Min Lin
Bootstrapping Language Models with DPO Implicit Rewards
Proceedings of ICLR, 2025 [pdf] [code]
MHFAIA @ ICML, 2024

Wenjun Li, Changyu Chen, Pradeep Varakantham
Unlocking Large Language Model's Planning Capabilities with Maximum Diversity Fine-tuning
Findings of NAACL, 2025 [pdf]

Zichang Ge^*, Changyu Chen^*, Arunesh Sinha, Pradeep Varakantham
On Learning Informative Trajectory Embeddings for Imitation, Classification and Regression
Proceedings of AAMAS, 2025 [pdf] [code]

Zichen Liu, Changyu Chen, Chao Du^†, Wee Sun Lee, Min Lin
Sample-Efficient Alignment for LLMs
LanGame @ NeurIPS, 2024 [pdf] [code]

Changyu Chen, Ramesha Karunasena, Thanh Hong Nguyen, Arunesh Sinha, Pradeep Varakantham
Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning
Proceedings of NeurIPS, 2023 [pdf] [project page] [code]

Changyu Chen, Avinandan Bose, Shih-Fen Cheng, Arunesh Sinha
Multiscale Generative Models: Improving Performance of a Generative Model Using Feedback from Other Dependent Generative Models
Proceedings of AAAI, 2022 [pdf] [code]

^† denotes corresponding author. ^* denotes equal contribution.