About Me
I’m an undergraduate at Shanghai Jiao Tong University (SJTU), pursuing a B.S. in Engineering. (expected Jun 2026). I’m now a research intern in the Northwestern-MLL-Lab, advised by Prof. Manling Li. My work currently focuses on spatial understanding. Prior to this, I was an intern at the Shanghai AI Lab, contributing to the post-training of InternLM3.
Research interests
My current research centers around the following domains:
- Multimodal Foundation Models: Towards Unifying Perception and Generation
- Spatial Intelligence and World Models.
📝 Publications
ICLR 2026
What Lies Beyond the View? Actively Constructing Spatial Beliefs in Foundation Models, Pingyue Zhang*, Zihan Huang*, Yue Wang*, Jieyu Zhang*, Letian Xue, Zihan Wang, Qineng Wang, Keshigeyan Chandrasegaran, Ruohan Zhang, Yejin Choi, Ranjay Krishna, Jiajun Wu, Li Fei-Fei, Manling Li
- Proposed the Theory of Space (ToS), a novel framework to evaluate an agent’s ability to build a genuine spatial understanding of an environment through active, curiosity-driven exploration.
📖 Educations
- 2022.09 — 2026.06 (expected), B.S. Engineering, Shanghai Jiao Tong University (SJTU), Shanghai, China.
💻 Internships
- 2025.05 — Present, Northwestern-MLL-Lab, Evanston, IL. Advisor: Prof. Manling Li. Focus: spatial understanding of large language model.
- 2025.03 — 2025.05, Bytedance Inc., Shanghai, China. Focus: data curation and post-training on E-commerce domain data
- 2024.11 — 2025.02, Shanghai AI Laboratory, Shanghai，China. Focus: post-training and data curation