I’m a final-year PhD student in Machine Learning at University of Cambridge and Max Planck Institute for Intelligent Systems under the Cambridge-Tübingen PhD Fellowship, advised by Prof. José Miguel Hernández-Lobato and Prof. Bernhard Schölkopf. I interned at Microsoft Research during my PhD.

I’m generally keen on core machine learning research and its applications in the physical world. My current research interests center around image and video generation, world modeling, embodied AI, and multimodal learning with diffusion and autoregressive models.

Previously, my PhD research focused on probabilistic machine learning and its scientific applications. I developed novel meta-learning, generative modeling and enhanced sampling methods to enable data-efficient molecular property prediction, accelerated molecular configuration sampling, and uncertainty-aware machine learning force field modeling. My previous research also investigated the training dynamics of deep neural networks, including analyzing the characteristic activations of ReLU neural networks, developing optimal sampling schemes for distributed optimization of neural networks, and examining the behaviors in joint training of deep ensembles.