I am a third-year undergraduate student at Zhejiang University, majoring in Computer Science & Technology at the Chu Kochen Honors College. I am currently a research intern at Tsinghua University, where I work on model-based reinforcement learning and world models.

I am obsessed with one question: “what is the realizable path toward physical intelligence?” Through my previous work on LM interpretability and continuous reasoning, I came to realize that today’s models achieve abstraction on top of text and 2D visual tokens, but these foundations are not enough for true spatial intelligence. I believe the next-generation physical AI will require new model architectures with built-in 3D inductive biases and new training representations for spatial understanding. My broader ambition is to help “turn AI into a physically grounded assistant beyond the screen”.

My long-term goal is to develop physically grounded, agentic models.

News

[2025-2026] One paper submitted (under review with strong feedback).
[2025. 10] Started research at Tsinghua University on physical world models and RL exploration.
[2025. 10] Awarded First-Class Scholarship, Zhejiang University.
[2024. 10] Awarded National Scholarship (Top 0.5%) & First-Class Scholarship, Zhejiang University.

Publications

• Mind Dreamer: Untethering Imagination via Active Counterfactual Reasoning on Latent Manifolds
  Shaojun Xu, Xiaoling Zhou, Yihan Lin, Yapeng Meng, Xinglong Ji, Luping Shi, Rong Zhao
  PDF