Arash Vahdat

La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching

Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute

Exploring Synthesizable Chemical Space with Iterative Pathway Refinements

Esoteric Language Models

On Equivariance and Fast Sampling in Video Diffusion Models Trained with Warped Noise

Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference

ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids

Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics

GenMol: A Drug Discovery Generalist with Discrete Diffusion

Not-So-Optimal Transport Flows for 3D Point Cloud Generation

Truncated Consistency Models

Energy-Based Diffusion Language Models for Text Generation

Proteina: Scaling Flow-based Protein Structure Generative Models

Heavy-Tailed Diffusion Models

Adaptive Flow Matching for Resolving Small-Scale Physics

Stochastic Flow Matching for Resolving Small-Scale Physics

CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation