I’m a Research Scientist at Bosch Research and Tsinghua-Bosch Joint Research Center on Machine Learning. I’m generally keen on core machine learning and artificial intelligence research, as well as their applications in the physical world. My current research focuses on diffusion models, multimodal foundation models and world models for autonomous driving and embodied AI. I also work on LLM code generation and optimization for large-scale industrial problems.

Previously, I received my PhD in Machine Learning from University of Cambridge and Max Planck Institute for Intelligent Systems through the Cambridge-Tübingen PhD Fellowship, advised by Prof. José Miguel Hernández-Lobato and Prof. Bernhard Schölkopf. During my PhD studies, I interned at Microsoft Research. My doctoral research focused on probabilistic machine learning and its scientific applications, with a particular interest in the synergy between deep learning and probabilistic inference. I developed novel methods in meta-learning, generative modeling, and enhanced sampling for media synthesis and scientific discovery. I also studied neural network optimization and training dynamics, with the goal of understanding and improving modern deep neural networks.