About Me

I am a 3rd-year undergraduate student at Tsinghua University, majoring in Electronic Engineering. My research interests focus on 3D Vision, Video Generation, and Multimodal Large Language Models (MLLMs).

Currently, I am an Undergraduate Research Assistant at the Lab of Prof. Yueqi Duan at Tsinghua University. I am passionate about building intelligent systems that can perceive and understand the physical world in 3D.

Education

• Tsinghua University, Beijing, China (Sept 2023 – Present)
  • B.Eng. in Electronic Engineering
  • GPA: 3.96/4.0 (Rank: 6/265, top 3%)
  • Selected Courses: Advanced Calculus, Linear Algebra, Probability and Stochastic Process, Signals and Systems, Programming Basics (C/C++), Data Structures and Algorithms, Media and Recognition.

Research Interests

• 3D Vision & Spatial Intelligence: Understanding 3D structures and spatial relationships from 2D/3D inputs.
• Video Generation: Developing controllable and high-fidelity video generation frameworks.
• Multimodal Models: Finetuning and scaling MLLMs for enhanced perception and reasoning.

News

• [Mar. 2025] Our paper Video-T1: Test-Time Scaling for Video Generation has been accepted to ICCV 2025!
• [Feb. 2026] Released preprint: Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training.