Weirui Ye 叶葳蕤

Postdoctoral Fellow · MIT CSAIL

I am a postdoctoral fellow in the LIS Group at MIT CSAIL, working with Leslie Pack Kaelbling and Tomás Lozano-Pérez at MIT, and Yilun Du at Harvard. I received my Ph.D. from Tsinghua University, advised by Yang Gao, and my B.Sc. from Tsinghua as well. During my Ph.D., I was also a visiting scholar at UC Berkeley, working with Pieter Abbeel.

My research brings together reinforcement learning, generative world models, and agentic robotics to build robots that learn efficiently, generalize, and keep improving.

News

Sep. 2026Invited to serve as an Area Chair for ICLR 2027.
Aug. 2026Co-organizing two CoRL 2026 workshops: Remember, Retrieve, Act: Memory for Robot Foundation Models and Compositional Generalization for Real-World Robot Learning.
Jul. 2026Selected as one of the AI25: 25 Under-25 AI Innovators by Sequoia China and MIT Technology Review China.

Earlier news

Nov. 2025Joined the LIS Group at MIT CSAIL as a postdoctoral fellow, advised by Leslie Pack Kaelbling.
Sep. 2024Reinforcement Learning with Foundation Priors was accepted as an Oral presentation at CoRL 2024.
May 2024EfficientZero V2 was accepted as a Spotlight at ICML 2024.
Mar. 2024Joined Berkeley Artificial Intelligence Research (BAIR) as a visiting scholar, working with Pieter Abbeel.

Selected Publications

Full list

* Equal contribution / co-lead · † Co-advisor · ‡ Co-corresponding author

2026

Energy-Based Policy Orchestration

Weirui Ye*, Yen-Jen Wang*, Elvis Hsieh*, Zhiyang Dou, Shibo Zhao, Pieter Abbeel, Yilun Du, Leslie Pack Kaelbling, Tomás Lozano-Pérez
CoRL 2026HierarchicalRobot Learning

Paper Code Project
Iterative Gumbel Planning for Continuous Control

Shaohuai Liu*, Weirui Ye*, Yilun Du‡, Le Xie‡
NeurIPS 2026RLGenerative & World ModelsPlanning & Reasoning

Paper Code Project
Scaling Online Exploration for Robot Agents

Runhan Huang*, Xiangcheng Zhang*, Haoyu Chen, Yitong Li, Yen-Jen Wang, Bohan Lyu, Haotian Ye, Chuye Hong, Yixuan Wang, Chloe Su, Haoyu Xiong, Yangzhen Wu, Enze Xie, Travis Manderson, Stefano Ermon, Pieter Abbeel, Antonio Torralba, Dawn Song, Weirui Ye, Yilun Du
arXiv 2026HierarchicalRobot LearningAgentic Robotics

Paper Code Project
Multimodal Filesystem Memory for Long-Horizon Embodied Agents

Chloe Su*, Jiahan Li*, Zhenting Qi, Chaoran Cheng, Haoyu Chen, Sejoon Jun, Weirui Ye, Yilun Du
arXiv 2026MemoryAgentic RoboticsGames

Paper Code Project
DriftWorld: Fast World Modeling through Drifting

Susie Lu, Haonan Chen, Weirui Ye, Yilun Du
arXiv 2026Generative & World Models

Paper Code Project
Temporal Backtracking Search for Test-time Generative Video Reasoning

Sejoon Jun, Zheng Ding, Chloe H. Su, Weirui Ye†, Yilun Du†
NeurIPS 2026Generative & World ModelsPlanning & ReasoningGames

Paper Project
Scaling Tasks, Not Samples: Mastering Humanoid Control through Multi-Task Model-Based Reinforcement Learning

Shaohuai Liu*, Weirui Ye*, Yilun Du†, Le Xie†
arXiv 2026RLGenerative & World ModelsRobot Learning

Paper Code Project
TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models

Zheng Ding*, Weirui Ye*
ICLR 2026RLGenerative & World Models

Paper Code Project

2025

Video2Policy: Scaling up Manipulation Tasks in Simulation through Internet Videos

Weirui Ye, Fangchen Liu, Zheng Ding, Yang Gao, Oleh Rybkin, Pieter Abbeel
arXiv 2025Robot LearningAgentic Robotics

Paper Project

2024

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
CoRL 2024 Oral · 4%RLRobot Learning

Paper Project
EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data

Shengjie Wang*, Shaohuai Liu*, Weirui Ye*, Jiacheng You, Yang Gao
ICML 2024 Spotlight · 3.5%RLGenerative & World ModelsGames

Paper Code