Dr. Lai is a Research Scientist and Tech Lead on Sony AI’s Music Foundation Model Team, where he focuses on deep generative modeling and robustness, with particular emphasis on the theoretical foundations of diffusion models in collaboration with Prof. Stefano Ermon. He also serves as a Visiting Assistant Professor in the Applied Mathematics Department at National Yang Ming Chiao Tung University, working with Prof. Ming-Chih Lai to supervise students and advance research in deep learning methods for partial differential equations.
His current research focuses on advancing diffusion models, including improving sample quality and diversity, accelerating sampling, and enabling controllable generation. He is also interested in inverse problems through the use of generative models. In addition, he explores mathematically explainable AI, seeking to elucidate the underlying mechanisms of artificial intelligence through rigorous mathematical frameworks.

Sophia Tang is a researcher in generative modeling and AI for science at the University of Pennsylvania, advised by Dr. Pranam Chatterjee. Her research ranges from developing multi-objective RL and guidance techniques for discrete diffusion to theoretical Schrödinger bridge frameworks for generative modelling of branching and interacting particle systems. She focuses on developing principled generative modeling techniques for scientific and biological applications, including therapeutic design (e.g., peptides, mRNA, and small molecules), cell-state simulation, and molecular dynamics.

In addition to her research, she writes long-form tutorial papers on foundational topics in machine learning. Her recent works include “Foundations of Schrödinger Bridges for Generative Modeling” (220 pages) and “A Complete Guide to Spherical Equivariant Graph Transformers” (99 pages), which aim to make advanced theoretical concepts accessible to a broader audience.