Joey Bose

Efficient Regression-based Training of Normalizing Flows for Boltzmann Generators

OXtal: An All-Atom Diffusion Model for Organic Crystal Structure Prediction

Planner Aware Path Learning in Diffusion Language Models Training

Generalised Flow Maps for Few-Step Generative Modelling on Riemannian Manifolds

Path Planning for Diffusion Language Model Sampling

Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities

The Superposition of Diffusion Models Using the Itô Density Estimator

RETRO SYNFLOW: Discrete Flow-Matching for Accurate and Diverse Single-Step Retrosynthesis

Curly Flow Matching for Learning Non-gradient Field Dynamics

Scalable Equilibrium Sampling with Sequential Boltzmann Generators

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction