Shaofeng Yin
About Me
I am currently a senior undergraduate at Tsinghua University, pursuing a degree in Information and Computing Science.
In the summer of 2023, I joined THUML, working with Prof. Mingsheng Long. In the summer of 2024, I began a research internship at Lecar Lab, under the guidance of Prof. Guanya Shi. I am now visiting the Stanford Vision and Learning Lab, adviced by Prof. Jiajun Wu and Prof. C. Karen Liu.
My current research interests lie in deep learning for generalizable world modeling, humanoid control, and robotic manipulation.
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!
Research
-
arxiv
arxiv, 2025.Research question: How can we develop a sim-to-real visual whole-body control framework for humanoid loco-manipulation?Key features: Visuomotor policies; Whole-body dexterity; In-the-wild deployment; Humanoid loco-manipulation. -
Neurlps
Conference on Neural Information Processing Systems (Neurlps), 2025.Research question: How can we train world models to better serve downstream tasks, beyond mere transition modeling?Key features: RLVR training; strong improvements on language and video world models across text games, web navigation, and robot manipulation. -
ICML
International Conference on Machine Learning (ICML), 2025.Research question: How can we build generalizable sensor-based world models across diverse environments?Key features: pretrained proprioceptive world model; single model for all robots; strong transferability; significant improvements in MPC and OPE. -
Neurlps
Conference on Neural Information Processing Systems (Neurlps), 2024.Research question: How can we leverage the advancements in scalable video generative models for developing interactive visual world models?Key features: pretrained visual world model; unified model for diverse robot arms; strong transferability; high efficiency; significant improvements across MPC and MBRL on manipulation tasks.
Experience
Honors & Awards
- [2025] SenseTime Scholarship (Top 30 undergraduates in China)
- [2024] Grand Prize (Top Award), Student Academic Training Program, Tsinghua University (5/1852)
- [2024] Outstanding Poster Award, Student Academic Research Advancement Program, Tsinghua University (36/357)
- [2024] Comprehensive Excellence Award of Tsinghua University
- [2024] Spark Scientific and Technological Innovation Fellowship (top 1%, most prestigious and selective academic organization for students at Tsinghua University)
- [2023] The First Prize of (National) Regional College Students’ Physics Contest
- [2023] Comprehensive Excellence Award of Tsinghua University
- [2023] Outstanding Academic Scholarship of Tsinghua University
Education
- B.S. in Information and Computing Science, Tsinghua University, 2022-2026 (expected)
Zhili College, Tsinghua University
GPA: 3.95/4.00, Major GPA: 4.00/4.00, Major Rank: 1/30.
Selected Courses:Numerical Analysis (A+), Students Research Training (A+), Artificial Neural Networks (A+), Principles of Signal Processing (A+), Abstract Algebra (A+), Discrete Mathematics (A+), Mathematical Programming (A), Introduction to Machine Learning (A), Measures and Integrals (A), Complex Analysis (A)
Projects
-
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. -
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).