avatar

Shaofeng Yin

Undergraduate Student
Tsinghua University
ysf22 (at) mails.tsinghua.edu


About Me

I am currently a third-year undergruduate at Tsinghua University, pursuing a degree in Information and Computing Science.

In the summer of 2023, I joined THUML under the supervision of Prof. Mingsheng Long. In the summer of 2024, I began a research internship at Lecar Lab, under the guidance of Prof. Guanya Shi.

My research aims to develop general algorithms that empower agents to learn efficiently in sequential, interactive, and dynamic environments. Currently, I am particularly excited about exploring effective deep learning methods for physical scene understanding and general-purpose world modeling.

News

Research

  1. arXiv
    Trajectory World Models for Heterogeneous Environments
    Shaofeng Yin*, Jialong Wu*, Siqiao Huang, Xingjian Su, Xu He, Jianye Hao, Mingsheng Long
    arXiv preprint, 2025.
    PDF

  2. Neurlps
    iVideoGPT: Interactive VideoGPTs are Scalable World Models
    Jialong Wu*, Shaofeng Yin*, Ningya Feng, Xu He, Dong Li, Jianye Hao, Mingsheng Long
    Conference on Neural Information Processing Systems (Neurlps), 2024.
    PDF Code Project Page

Experience

  1. LeCAR Lab, CMU Robotics Institute
    Visiting Researcher
    July - Aug. 2024

  2. THUML, Tsinghua University
    Research Assistant
    Sept. 2023 - Now

Projects

  1. RISC-V Pipeline Processor
    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.
    PDF

  2. Path-Tracing Renderer
    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).
    PDF Code

Education

Honors & Awards