Weirui | Tsinghua University

About Me

I am a last year Ph.D student in Institute for Interdisciplinary Information Science (IIIS) at Tsinghua University, advised by Prof. Yang Gao. During my Ph.D., I also work consistently with Prof. Pieter Abbeel in reinforcement learning and robot learning. Previously, I received my bachelor degree from the School of Software at Tsinghua University, where I conducted research under the supervision of Prof. Mingsheng Long and Prof. Feng Xu.

My research goal is to develop human-level, sample-efficient policy learning algorithms for robots. My current interest lies in model-based reinforcement learning, internet-scale prior knowledge for policy learning, and robot learning.

News from 2024

[Sep. 2024] Our paper Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own was accepted as Oral by CoRL 2024.
[May. 2024] Our paper EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data was accepted as Spotlight by ICML 2024.
[Mar. 2024] I embarked on my visiting scholar journey at Berkeley Artificial Intelligence Research (BAIR) under the expert guidance of Prof. Pieter Abbeel.

Publications

CoRL

Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own

Weirui Ye, Yunsheng Zhang, Haoyang Weng, Xianfan Gu, Shengjie Wang, Tong Zhang, Mengchen Wang, Pieter Abbeel, Yang Gao

Conference on Robot Learning (CoRL), 2024.

PDF Code Website Oral, 4%

ICML

EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data

Shengjie Wang*, Shaohuai Liu*, Weirui Ye*, Jiacheng You, Yang Gao (*equal contribution)

International Conference on Machine Learning (ICML), 2024.

PDF Code Spotlight, 3.5%

ICLR

Seer: Language Instructed Video Prediction with Latent Diffusion Models

Xianfan Gu, Chuan Wen, Weirui Ye, Jiaming Song, Yang Gao

International Conference on Learning Representations (ICLR), 2024.

PDF Code Website

ICLR

Become a Proficient Player through Watching Pure Videos

Weirui Ye*, Yunsheng Zhang*, Pieter Abbeel, Yang Gao (*equal contribution)

International Conference on Learning Representations (ICLR), 2023.

PDF Code

ICLR

SpeedyZero: Mastering Atari with Limited Data and Time.

Mei Yixuan*, Jiaxuan Gao*, Weirui Ye, Shaohuai Liu, Yang Gao, Yi Wu

International Conference on Learning Representations(ICLR), 2023.

PDF

NeurIPS

Spending Thinking Time Wisely: Accelerating MCTS with Virtual Expansions

Weirui Ye, Pieter Abbeel, Yang Gao

Conference on Neural Information Processing Systems(NeurIPS), 2022.

PDF

NeurIPS

Planning for sample efficient imitation learning

Zhao-Heng Yin, Weirui Ye, Qifeng Chen, Yang Gao

Conference on Neural Information Processing Systems(NeurIPS), 2022.

PDF Code

NeurIPS

Mastering Atari Games with Limited Data

Weirui Ye, Shaohuai Liu, Thanard Kurutach, Pieter Abbeel, Yang Gao

Conference on Neural Information Processing Systems(NeurIPS), 2021.

PDF Code Towards Data Science Interview Tsinghua News (Chinese) YouTube

AAAI

Simultaneous Learning of Pivots and Representations for Cross-domain Sentiment Classification

Liang Li, Weirui Ye, Mingsheng Long, Jianmin Wang

Association for the Advancement of Artificial Intelligence(AAAI), 2020.

PDF

AAAI

Transferable Attention for Domain Adaptation

Ximei Wang, Liang Li, Weirui Ye, Mingsheng Long, Jianmin Wang

Association for the Advancement of Artificial Intelligence(AAAI), 2019.

PDF