Publications

Can Simple Denoising Improve Uniform State Diffusion Models
Huaisheng Zhu, Zhengyu Chen, Shijie Zhou, Zhihui Xie, Yige Yuan, Shiqi Chen, Zhimeng Guo, Siyuan Xu, Hangfan Zhang, Teng Xiao, Vasant G. Honavar
International Conference on Machine Learning (ICML 2026).

Adaptive Code Watermarking Through Reinforcement Learning
Zhimeng Guo, Huaisheng Zhu, Siyuan Xu, Hangfan Zhang, Teng Xiao, Minhao Cheng
International Conference on Machine Learning (ICML 2026).

Efficient Safe Meta-Reinforcement Learning: Provable Near-Optimality and Anytime Safety
Siyuan Xu, Minghui Zhu
Neural Information Processing Systems (NeurIPS 2025).

Meta-Reinforcement Learning with Human-in-the-Loop Adaptation via Preference-Order-Preserving Task Embedding
Siyuan Xu, Minghui Zhu
International Conference on Machine Learning (ICML 2025).

Explainable Reinforcement Learning from Human Feedback to Improve Large Language Model Alignment
Shicheng Liu, Siyuan Xu, Wenjie Qiu, Hangfan Zhang, Minghui Zhu
Neural Information Processing Systems (NeurIPS 2025).

Simple Distillation for One-Step Diffusion Models
Huaisheng Zhu, Teng Xiao, Shijie Zhou, Zhimeng Guo, Hangfan Zhang, Siyuan Xu, Vasant G Honavar
Neural Information Processing Systems (NeurIPS 2025).

Reinforcement Learning for Large Language Models via Group Preference Reward Shaping
Huaisheng Zhu, Siyuan Xu, Hangfan Zhang, Teng Xiao, Zhimeng Guo, Shijie Zhou, Shuyue Hu, Vasant G Honavar
Conference on Empirical Methods in Natural Language Processing (EMNLP, main track) 2025.

Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator
Siyuan Xu, Minghui Zhu
Neural Information Processing Systems (NeurIPS 2024).

Online Constrained Meta-Learning: Provable Guarantees for Generalization
Siyuan Xu, Minghui Zhu
Neural Information Processing Systems (NeurIPS 2023), Spotlight, Top 3.6%.

Efficient Gradient Approximation Method for Constrained Bilevel Optimization
Siyuan Xu, Minghui Zhu
AAAI Conference on Artificial Intelligence (AAAI 2023), Oral.

Federated Reinforcement Learning for Generalizable Motion Planning
Zhenyuan Yuan, Siyuan Xu, Minghui Zhu
American Control Conference (ACC) 2023.

Secure Perception-Driven Control of Mobile Robots Using Chaotic Encryption
Xu Zhang, Zhenyuan Yuan, Siyuan Xu, Yang Lu, Minghui Zhu
American Control Conference (ACC) 2023.

Meta Value Learning for Fast Policy-Centric Optimal Motion Planning
Siyuan Xu, Minghui Zhu
Robotics: Science and Systems (RSS) 2022.