Full Publications

* denotes equal contribution. Alphabetical author order is noted separately.

Preprints

• Chenlu Ye*, Xuanchang Zhang*, Yifan Hao*, Zhou Yu, Ziji Zhang, Abhinav Gullapalli, Hao Chen, Jing Huang, Tong Zhang, “Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL”, Preprint. Code | blog.

• Wei Xiong*, Chenlu Ye*, Baohao Liao*, Hanze Dong*, Xinxing Xu, Christof Monz, Jiang Bian, Nan Jiang, Tong Zhang, “Reinforce-Ada: An Adaptive Sampling Framework under Non-linear RL Objectives”, Preprint. Code.

• Chenlu Ye, Zhou Yu, Ziji Zhang, Hao Chen, Narayanan Sadagopan, Jing Huang, Tong Zhang, Anurag Beniwal, “Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training”, Preprint.

• Wei Xiong*, Hanning Zhang*, Chenlu Ye*, Lichang Chen, Nan Jiang, Tong Zhang, “Self-rewarding correction for mathematical reasoning”, Preprint.

• Jianqing Fan, Zhaoran Wang, Zhuoran Yang, Chenlu Ye (alphabetical author order), “Provably Efficient High-Dimensional Bandit Learning with Batched Feedbacks”, Preprint.

• Xingyuan Pan*, Chenlu Ye*, Joseph Melkonian*, Jiaqi W. Ma, Tong Zhang, “Daunce: Data Attribution through Uncertainty Estimation”, Preprint.

• Yifan Hao*, Chenlu Ye*, Chi Han, Tong Zhang, “Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models”, Preprint.

Peer-Reviewed Publications

2025

• Heyang Zhao, Chenlu Ye, Quanquan Gu, Tong Zhang, “Sharp Analysis for KL-Regularized Contextual Bandits and RLHF”, NeurIPS 2025.

• Chenlu Ye, Yujia Jin, Alekh Agarwal, Tong Zhang, “Catoni Contextual Bandits are Robust to Heavy-tailed Rewards”, ICML 2025 Spotlight.

• Heyang Zhao*, Chenlu Ye*, Wei Xiong, Quanquan Gu, Tong Zhang, “Logarithmic Regret for Online KL-Regularized Reinforcement Learning”, ICML 2025.

• Yifan Hao*, Xingyuan Pan*, Hanning Zhang*, Chenlu Ye, Rui Pan, Tong Zhang, “Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods”, ICML 2025.

• Yong Lin*, Chen Liu*, Chenlu Ye*, Qing Lian, Yuan Yao, Tong Zhang, “Optimal Sample Selection Through Uncertainty Estimation and Its Application in Deep Learning”, JMLR 2025.

2024

• Chenlu Ye*, Wei Xiong*, Yuheng Zhang*, Hanze Dong*, Nan Jiang, Tong Zhang, “Online iterative reinforcement learning from human feedback with general preference model”, NeurIPS 2024. Code.

• Wei Xiong*, Hanze Dong*, Chenlu Ye*, Ziqi Wang, Han Zhong, Heng Ji, Nan Jiang, Tong Zhang, “Iterative preference learning from human feedback: Bridging theory and practice for RLHF under KL-Constraint”, ICML 2024.

• Chenlu Ye*, Jiafan He*, Quanquan Gu, Tong Zhang, “Towards robust model-based reinforcement learning against adversarial corruption”, ICML 2024.

2023

• Chenlu Ye*, Rui Yang*, Quanquan Gu, Tong Zhang, “Corruption-Robust Offline Reinforcement Learning with General Function Approximation”, NeurIPS 2023.

• Chenlu Ye, Wei Xiong, Quanquan Gu, Tong Zhang, “Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes”, ICML 2023.