About 🔬

I'm a fourth-year undergraduate student at Xi'an Jiaotong University, majoring in Artificial Intelligence. My research interests lie in Virtual World Models generative systems that can create physically coherent yet imaginative virtual worlds. Rather than imitating reality, I aim to build models that can invent new, explorable worlds: 4D environments that evolve over time, obey self-consistent (real or virtual) physics, and host interactive agents and NPCs capable of acting and living within them. Ultimately, I hope to bridge the precision of physics with the creativity of imagination, enabling AI to become not only an observer of the world, but a creator of worlds.

To achieve this vision, my current interests include three interconnected directions::

1. 3D/4D content generation — generating the appearance and dynamics of evolving worlds;
2. Agent and NPC behavior modeling — enabling entities to plan, act, and interact coherently;
3. Physics law injection — embedding learnable or designed physical rules, whether real or virtual, to ensure consistent world evolution.

I am now a Research Intern at the Stanford Vision and Learning Lab (SVL) and work closely with Koven Yu and Prof. Jiajun Wu on 3D visual generation. Meanwhile, I'm a Research Intern at ZJU3DV, Zhejiang University, working with Prof. Sida Peng and Prof. Xiaowei Zhou on Robust 3D Reconstruction. Previously, I work with Prof. Xiangyong Cao and Prof. Deyu Meng on low level image processing at Xi'an Jiaotong University.