Jiahao Zhan 「詹佳豪」

I am a senior undergraduate student at Fudan University, majoring in Artificial Intelligence. Currently, I am a research intern at CUHK MMLab, advised by Tianfan Xue, and an intern at ByteDance.

In past years, I had the pleasure of collaborating with Dequan Wang at Shanghai Jiao Tong University, Hang Zhao at Tsinghua University, Qifeng Chen at HKUST, and Jiajun Wu at Stanford University.

Email  /  CV  /  Google Scholar  /  Github

Hover over the photo 👆

Research

I'm interested in leveraging generative models as neural simulators, including improving the physical realism of video models and enhancing their memory capabilities. Some papers are highlighted.

A hybrid generative simulator enabling long-horizon, action-conditioned 4D scene generation from a single image via a unified representation that links physical state and visual primitives.

An efficient reward modeling framework inspired by GANs that eliminates manual preference annotation, training through discrimination between target samples and model-generated outputs.

A scalable motion planner using ViT encoder and MoE causal Transformer that generalizes better across different driving scenarios.

A live benchmark leveraging 25,000+ image-text pairs from top-tier journals to evaluate MLLMs' cross-modal scientific reasoning.

Projects

The Third Prize

The Second Prize

Research Experiences

Website template from Jon Barron.