About Me

I am a sophomore majoring in Computer Science at the IIIS, Tsinghua University. Currently, I am an intern at MIT CSAIL, supervised by Professor Kaiming He. My research interests lie in computer vision and deep generative models. I am particularly fascinated by simple yet effective model designs.

Before entering college, I competed in the Physics Olympiad during high school and won a gold medal in the 39th CPhO. Afterward, I spent one preparatory year at IIIS, Tsinghua University, where I built a solid foundation in the mathematical principles underlying computer science and deep learning. I am fortunate to conduct research under the supervision of Professor Huazhe Xu during this period.

Although I am still early in my research journey, I am eager to explore opportunities in both academia and industry. I also enjoy connecting with people who share similar interests and discussing everything from research ideas to personal experiences. Feel free to reach out if you’d like to connect!

My resume is linked here.

Education

IIIS, Tsinghua University

Undergraduate Student

Beijing, China, Sep 2024 - Present

Major GPA: 4.00/4.00, with 13/21 A+ (Top ~5%) and 8/21 A (Top ~25%)

Publications

A Minimalist Baseline for Text-to-Image Generation

Xianbang Wang†, Hanhong Zhao‡, Yiyang Lu‡, Kangyang Zhou, Linrui Ma, Kaiming He§

† Project lead, ‡ Core contributor, § Supervisor

Blog post, 2026

[Project Page] [PyTorch] [JAX]

ELF: Embedded Language Flows

Keya Hu*, Linlu Qiu*, Yiyang Lu, Hanhong Zhao, Tianhong Li, Yoon Kim, Jacob Andreas, Kaiming He

arXiv preprint, 2026

[Paper] [arXiv] [Code]

One-step Latent-free Image Generation with Pixel Mean Flows

Yiyang Lu*, Susie Lu*, Qiao Sun*, Hanhong Zhao*, Zhicheng Jiang, Xianbang Wang, Tianhong Li, Zhengyang Geng, Kaiming He

International Conference on Machine Learning (ICML) 2026

[Paper] [arXiv] [Code]

Bidirectional Normalizing Flow: From Data to Noise and Back

Yiyang Lu*†, Qiao Sun*†, Xianbang Wang*, Zhicheng Jiang, Hanhong Zhao, Kaiming He

* Equal technical contribution, † Project lead

Computer Vision and Pattern Recognition (CVPR) 2026 (Highlight)

[Paper] [arXiv] [Code]

Improved Mean Flows: On the Challenges of Fastforward Generative Models

Zhengyang Geng*, Yiyang Lu*, Zongze Wu, Eli Shechtman, J. Zico Kolter, Kaiming He

Computer Vision and Pattern Recognition (CVPR) 2026 (Highlight)

[Paper] [arXiv] [Code]

H³DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learning

Yiyang Lu*, Yufeng Tian*, Zhecheng Yuan*, Xianbang Wang, Pu Hua, Zhengrong Xue, Huazhe Xu

International Conference on Learning Representations (ICLR) 2026

[Project Page] [Paper] [arXiv]

Selected Awards

SenseTime Scholarship

Top 30 Undergraduates Nationwide

SenseTime, 2026

Sparking Program

Top 1% in Tsinghua

Tsinghua University, 2026

National Scholarship

Top Scholarship in China

China, 2025

Freshman Scholarship

Scholarship for Outstanding Freshmen

Tsinghua University, 2024

The 39th Chinese Physics Olympiad (CPhO)

Gold Medal (Top 10)

Chinese Physics Olympiad, 2022