Yifu Yuan (袁逸夫)

PhD student, Tianjin University

I am a first-year PhD student at Deep Reinforcement Learning (DRL) Lab, Tianjin University (TJU), advised by Prof. Jianye Hao. I am also co-advised by Prof. Yan Zheng. I interned at Netease Fuxi AI Lab (Fuxi) during 2023, where I worked with Dr. Yujing Hu. I received my Bachelor's degree from the Dalian University of Technology (DUT), advised by Prof. Guozhen Tan.

Research interest

I am broadly interested in research on the building embodied agents for decision making. To achieve this, my current research interest contains Model-based reinforcement learning, Diffusion Model, RLHF and LLM agents. I hope to ride the wave of AI changing the world.


Publications and preprints

Papers sorted by recency. Authors with equal contribution are marked by *. Representative papers are highlighted.

KISA: A Unified Keyframe Identifier and Skill Annotator for Long-Horizon Robotics Demonstrations
Longxin Kou, Fei Ni, YAN ZHENG, Jinyi Liu, Yifu Yuan, Zibin Dong, Jianye HAO
International Conference on Machine Learning (ICML), 2024
A Method on Searching Better Activation Functions
Haoyuan Sun, Zihao Wu, Bo Xia, Pu Chang, Zibin Dong, Yifu Yuan, Yongzhe Chang, Xueqian Wang
SheetAgent: A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Models
Yibin Chen*, Yifu Yuan*, Zeyu Zhang, Yan Zheng, Jinyi Liu, Fei Ni, Jianye HAO
IJCAI2024 Automates Workshop
project page / arXiv
CriticGPT: Multimodal LLM as a Critic for Robot Manipulation
Jinyi Liu*, Yifu Yuan*, Jianye HAO, Fei Ni, Lingzhi Fu, Yibin Chen, Yan Zheng
AAAI2024 RL+LLMs Workshop
project page / arXiv
DiffuserLite: Towards Real-time Diffusion Planning
Zibin Dong, Jianye Hao, Yifu Yuan, Fei Ni, Yitian Wang, Pengyi Li, Yan Zheng
project page / arXiv
Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback
Yifu Yuan, Jianye Hao, Yi Ma, Zibin Dong, Hebin Liang, Jinyi Liu, Zhixin Feng, Kai Zhao, Yan Zheng
International Conference on Learning Representations (ICLR), 2024
project page / arXiv / benchmark / platform
AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
Zibin Dong*, Yifu Yuan*, Jianye Hao, Fei Ni, Yao Mu, Yan Zheng, Yujing Hu, Tangjie Lv, Changjie Fan, Zhipeng Hu
International Conference on Learning Representations (ICLR), 2024
NeurIPS Diffusion Workshop, 2023
project page / arXiv / code / dataset
ED2: Environment Dynamics Decomposition World Models for Continuous Control
Jianye Hao, Yifu Yuan* (student first author), Cong Wang, Zhen Wang
Submitted to TNNLS
arXiv / code
MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL
Fei Ni, Jianye Hao, Yao Mu, Yifu Yuan, Yan Zheng, Bin Wang, Zhixuan Liang
International Conference on Machine Learning (ICML), 2023
project page / arXiv
EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model
Yifu Yuan, Jianye Hao, Fei Ni, Yao Mu, Yan Zheng, Yujing Hu, Jinyi Liu, Yingfeng Chen, Changjie Fan
International Conference on Learning Representations (ICLR), 2023
NeurIPS DeepRL workshop, 2022
project page / pretrained model / arXiv / code

Education & Internship Experiences

Invited Talks

Academic Service

Reviewers: ICML2024, UAI2024, ECAI2024, NeurIPS 2024



I'm very welcome to any kind of collaboration or discussion. Feel free to contact me via email at
yuanyf [at] tju.edu.cn.