About

I am a PhD candidate in physics in the Department of Neurophysics at the Max Planck Institute for Human Cognitive and Brain Sciences in Leipzig, and a member of the International Max Planck Research School on Cognitive NeuroImaging (IMPRS CoNI). I started my PhD in 2024. My PhD is supervised by Nikolaus Weiskopf and Nico Scherf, with Martin Weigert (TU Dresden) as external advisor.

Research

I am interested in adapting pretrained generative models to new tasks and conditions, through fine-tuning and test-time adaptation. My current work develops these ideas for diffusion models, with simulation-based inference and inverse problems as testbeds.

My PhD project is on deep image reconstruction for fast, ultra-high-resolution MRI. It has given me hands-on experience with real forward models, acquisition constraints, and large experiments on HPC systems.

Background

Before my PhD, I studied automation (BSc, 2021) and control science and engineering (MSc, 2024) at the Beijing Institute of Technology, where I worked on medical image analysis: cardiac MRI segmentation and machine-learning assessment of pulmonary hypertension from CT pulmonary angiography.

Contact

The best way to reach me is by email at zhaox@cbs.mpg.de.

• Email
• GitHub
• Google Scholar
• LinkedIn