Zibin Dong / 董子斌
Intern at Huawei Noah's Ark Lab. Master's student at TJU Deep Reinforcement Learning Lab.
I am a master’s student at the TJU Deep Reinforcement Learning Lab, advised by Prof. Jianye Hao and co-advised by Prof. Yan Zheng. I received my Bachelor’s degree from the Harbin Institution of Technology (Shenzhen) (HITsz) in 2023, advised by Prof. Qingbin Gao.
My research interests primarily focus on developing general embodied agents for decision-making. To accomplish this goal, my current research encompasses Reinforcement Learning (RL): Offline RL, Model-based RL, RL from Human Feedback (RLHF), Diffusion Models for decision-making, and LLM agents. I aspire to leverage the transformative power of AI in shaping the world. I am highly self-motivated and possess a strong passion for AI research. I am constantly seeking opportunities for research collaborations, research interns, and PhD. You can find detailed information about me in my CV. Feel free to contact me at zibindong@outlook.com or wechat dongzibin1112.
news
| May 01, 2025 | Two papers accepted by ICML 2025: “MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement Learning”, “R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language Models” |
|---|---|
| Jan 23, 2025 | One paper accepted by ICLR 2025: “Entropy-based Activation Function Optimization: A Method on Searching Better Activation Functions” |
| Sep 26, 2024 | Three papers accepted by NeurIPS 2024: “CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making”, “DiffuserLite: Towards Real-time Diffusion Planning”, “PERIA: Perceive, Reason, Imagine, Act via Holistic Language and Vision Planning for Manipulation” |
| Jan 15, 2024 | Two papers accepted by ICLR 2024: “Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model”, “Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback” |
| Aug 05, 2023 | One paper accepted by CIKM 2023: “A Hierarchical Imitation Learning-based Decision Framework for Autonomous Driving” |
selected publications
-
CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision MakingIn The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track, NeurIPS, 2024 -
DiffuserLite: Towards Real-time Diffusion PlanningIn The Thirty-eighth Annual Conference on Neural Information Processing Systems, NeurIPS, 2024 -
AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion ModelIn The Twelfth International Conference on Learning Representations, ICLR, 2024 -
PERIA: Perceive, Reason, Imagine, Act via Holistic Language and Vision Planning for ManipulationIn The Thirty-eighth Annual Conference on Neural Information Processing Systems, NeurIPS, 2024 -
KISA: A Unified Keyframe Identifier and Skill Annotator for Long-Horizon Robotics DemonstrationsIn Forty-first International Conference on Machine Learning, ICML, 2024 -
Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human FeedbackIn The Twelfth International Conference on Learning Representations, ICLR, 2024 -
A Hierarchical Imitation Learning-based Decision Framework for Autonomous DrivingIn Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, CIKM, 2023 - MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement LearningIn Forty-second International Conference on Machine Learning, ICML, 2025
- Entropy-based Activation Function Optimization: A Method on Searching Better Activation FunctionsIn The Thirteenth International Conference on Learning Representations, ICLR, 2025
- R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language ModelsIn Forty-second International Conference on Machine Learning, ICML, 2025
