Generative modeling, flow models, optimal transport, and protein design at the intersection of machine learning and life sciences
Active Developing generative models for sampling from Boltzmann distributions—combining normalizing flows, diffusion, and autoregressive models to generate equilibrium samples of molecular systems.
Active Developing state-of-the-art generative models including diffusion models and flow-based approaches with applications to molecular design, language modeling, and scientific computing.
Active Developing efficient computational methods for optimal transport with applications to single-cell biology, trajectory inference, and generative modeling.
Applying generative modeling to protein design, molecular structure prediction, and crystal structure prediction using SE(3)-invariant flow matching and all-atom diffusion models.
Active Developing generative models for discrete sequences—including diffusion language models, masked discrete diffusion, and one-step discrete generation—for language modeling and biological sequence design.
Active Developing machine learning methods to understand cellular development, state transitions, and responses to stimuli using single-cell omics data.