avatar

Shaofeng Yin

Undergraduate Student
Tsinghua University
yinshaofeng04 (at) gmail.com


About Me

I am currently a senior undergraduate at Tsinghua University, pursuing a degree in Information and Computing Science.

In terms of academic performance, I have maintained an average GPA of 3.95, ranking first in my major. I began my research under the supervision of Prof. Prof. Mingsheng Long, focusing on world modeling. In the summer of 2024, I interned at Lecar Lab at Carnegie Mellon University, advised by Prof. Guanya Shi, where I worked on model-based reinforcement learning and planning algorithm. I am currently visiting the Stanford Vision and Learning Lab, adviced by Prof. Jiajun Wu and Prof. C. Karen Liu, working on humanoid control.

My current research interests lie in humanoid control, generalizable world modeling, and robotic manipulation. I aim to build robust primitive skills for humanoids through sim-to-real reinforcement learning or by leveraging human data, and then integrate these skills with planning to accomplish complex tasks.

I am applying for a PhD position in 2026 Fall. Please drop me an email if you are interested in my research or just want to chat!

Invited Talks

Research

  1. In submission
    Shaofeng Yin*, Yanjie Ze*, Hong-Xing Yu, C. Karen Liu†, Jiajun Wu†

  2. ICML
    Shaofeng Yin*, Jialong Wu*, Siqiao Huang, Xingjian Su, Xu He, Jianye Hao, Mingsheng Long†
    International Conference on Machine Learning (ICML), 2025.

  3. Neurlps
    Jialong Wu*, Shaofeng Yin*, Ningya Feng, Xu He, Dong Li, Jianye Hao, Mingsheng Long†
    Conference on Neural Information Processing Systems (Neurlps), 2024.

  4. Neurlps
    Jialong Wu, Shaofeng Yin, Ningya Feng, Mingsheng Long†
    Conference on Neural Information Processing Systems (Neurlps), 2025.

Experience

  1. Research Intern
    Feb. 2025 - Now

  2. Research Intern
    July - Aug. 2024

  3. Research Intern
    Sept. 2023 - Now

.

Honors & Awards

Education

Projects

  1. A five-stage pipelined RISC-V 32-bit processor featuring interrupt and exception handling, user-mode virtual address translation via page tables, and performance enhancements through I-Cache, D-Cache (Writeback), and TLB, with additional support for peripherals such as VGA and Flash.

  2. A compact renderer featuring Next Event Estimation, supporting Glossy Material (Disney Principal BRDF), Texture Mapping, Normal Mapping, Motion Blur, Normal Interpolation, Depth of Field, and Mesh Rendering (accelerated with BVH).