Kaizhe Hu 胡 开哲
hkz22@mails.tsinghua.edu.cn

I'm a third year Computer Science PhD student at the Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University. Before that, I received my Bachelor's Degree at the Department of Electronic Engineering, Tsinghua University.

My primary interest of research is on combining knowledge of pretrained generative models to intelligent agents that can serve human. To that end, I've explored the area of embodied AI, reinforcement learning, and generative models.

I'm fortunate to be advised by Professor Huazhe(Harry) Xu. I'm currently visiting professor C. Karen Liu's lab at Stanford University.

Twitter / Github / Google Scholar

Updates

Research

Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion

Yongyuan Liang, Tingqiang Xu, Kaizhe Hu, Guangqi Jiang, Furong Huang, Huazhe Xu
Conference on Neural Information Processing Systems (Neurips) 2024, Poster; AFM Workshop, Oral, Jul. 2024
Website  •   ArXiv  •   Code  •   Twitter  •   Models&Dataset

Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation

Yuanchen Ju*, Kaizhe Hu*, Guowei Zhang, Gu Zhang, Mingrun Jiang, Huazhe Xu
European Conference on Computer Vision (ECCV) 2024, Jan. 2024
Website  •   ArXiv  •   Code  •   Twitter

Rethinking Transformers in Solving POMDPs

Chenhao Lu, Ruizhe Shi*, Yuyao Liu*, Kaizhe Hu, Simon Shaolei Du, Huazhe Xu
The International Conference on Machine Learning (ICML) 2024, Poster, May
ArXiv  •   Code

Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization

Lei Kun, Zhengmao He*, Chenhao Lu*, Kaizhe Hu, Gao Yang, Huazhe Xu
International Conference on Learning Representations (ICLR) 2024, Poster, Nov. 2023
Website  •   ArXiv  •   Code  •   Twitter

LfVoid: Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning?

Jialu Gao*, Kaizhe Hu*, Guowei Xu, Huazhe Xu
Conference on Neural Information Processing Systems (Neurips) 2023, Poster, Jul. 2023
Website  •   ArXiv  •   Twitter


RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization

Zhecheng Yuan*, Sizhe Yang*, Pu Hua, Can Chang, Kaizhe Hu, Xiaolong Wang, Huazhe Xu
Conference on Neural Information Processing Systems (Neurips) 2023 Datasets and Benchmarks Track, Poster, Jul. 2023
Website  •   ArXiv  •   Code

DeFog: Decision Transformer under Random Frame Dropping

Kaizhe Hu*, Ray Chen Zheng* , Yang Gao, Huazhe Xu
International Conference on Learning Representations (ICLR) 2023, Poster, Mar. 2023
Website  •   ArXiv  •   Code

EIL: Extraneousness-Aware Imitation Learning

Ray Chen Zheng*, Kaizhe Hu*, Zhecheng Yuan, Boyuan Chen, Huazhe Xu,
International Conference on Robotics and Automation (ICRA) 2023, Poster, Oct. 2022
Website  •   ArXiv  •   Code