Haofei Lu | Tsinghua University

About Me

I am currently a second-year M.S. student of Pervasive Computing Group, Department of Computer Science and Technology, Tsinghua University, advised by Prof. Junliang Xing and Prof. Yuanchun Shi.

My research interests mainly lie in deep generative models, robot learning, and reinforcement learning. I am now focusing on legged robot learning / co-designing, and leveraging diffusion models for generative embodied task-solving.

I am seeking a Ph.D. position for Fall 2026. If my research aligns with your interests, I would be happy to discuss potential opportunities.

News

[Feb. 2025] We released Habi, an efficient tool that accelerates slow diffusion planners into fast decision-makers, achieving 800+ Hz even on a laptop CPU. Here is the Project Page.
[Jan. 2025] Two of my first-author papers are accepted by ICLR 2025. BodyGen on embodiment co-deisgn is accepted by ICLR 2025 as Spotlight (5.1%) . Diffusion-Veteran on generative decision-making is accepted by ICLR 2025 as Spotlight (5.1%).
[Feb. 2024] One paper on agent exploration is accepted by ICLR 2024.
[Dec. 2023] As the team leader of Tsinghua, I led our team to win the National Runner-Up🏆 of Tencent AI Arena Open Competition, which is held by Tencent AI & Honor of Kings.

Publications

* Equal Contribution, † Corresponding Author

arXiv 2025

Habitizing Diffusion Planning for Efficient and Effective Decision Making

Haofei Lu, Yifei Shen, Dongsheng Li, Junliang Xing†, Dongqi Han†

arXiv preprint, 2025.

arXiv PDF Code Project Page BibTex

ICLR 2025

What Makes a Good Diffusion Planner for Decision Making?

Haofei Lu, Dongqi Han†, Yifei Shen, Dongsheng Li

International Conference on Learning Representations (ICLR), 2025.

Spotlight Presentation (5.1%)

arXiv PDF Code BibTex

ICLR 2025

BodyGen: Advancing Towards Efficient Embodiment Co-Design

Haofei Lu, Zhe Wu, Junliang Xing†, Jianshu Li, Ruoyu Li, Zhe Li, Yuanchun Shi

International Conference on Learning Representations (ICLR), 2025.

Spotlight Presentation (5.1%)

arXiv PDF Code Project Page BibTex

ICLR 2024

PAE: Reinforcement Learning from External Knowledge for Efficient Exploration

Zhe Wu*, Haofei Lu*, Junliang Xing†, You Wu, Renye Yan, Yaozhong Gan, Yuanchun Shi

International Conference on Learning Representations (ICLR), 2024.

PDF Code BibTex

IJCAI 2022

Universal Video Style Transfer via Crystallization, Separation, and Blending

Haofei Lu, Zhizhong Wang†

International Joint Conference on Artificial Intelligence (IJCAI), 2022.

PDF Code BibTex

Selected Honors

Scholarships & Awards

Microsoft Research “Stars of Tomorrow” Certificate (top 10% interns), MSRA, 2025
TangZeSheng Scholarship (top 3%), Tsinghua University, 2024
CCF Elite Collegiate Award (top 102 students nationwide), China Computer Federation, 2022
Provincial Outstanding Student (top 0.1%), Jiangsu Department of Education, 2022
Presidential Scholarship (top 1%), Southeast University, 2021
National Scholarship (top 0.2% students nationwide), China Ministry of Education, 2020

Competitions

🏆 National Runner-up of Tencent AI Arena: National Open Competition, Tencent AI & Honor of Kings, 2023. (THU Teamleader, with Shikun Sun, Yuxuan Liu, Ruyi Xu, Yang Wu). Here’s a photo of us 😊.
🏆 Meritorious Winner of Interdisciplinary Contest in Modeling (ICM), Consortium for Mathematics and Its Applications (COMAP), 2021 (With Ming Zhai, Yuchen Pan)
🏆 First Prize of Chinese Mathematics Competitions (CMC), Chinese Mathematical Society (CMS), 2020

Academic Services

Reviewer

International Conference on Learning Representations (ICLR)
Conference on Neural Information Processing Systems (NeurIPS)
International Conference on Autonomous Agents and Multi-agent Systems (AAMAS)
International Joint Conference on Artificial Intelligence (IJCAI)
Association for the Advancement of Artificial Intelligence (AAAI)

Teaching Assistant

Fundamentals of Programming (Fall 2024), Tsinghua University.
Computer Vision (Fall 2024), Tsinghua University.
Fundamentals of Programming (Fall 2023), Tsinghua University.