Carles Domingo-Enrich

Any-Order Flexible Length Masked Diffusion

Test-time scaling of diffusions with flow maps

Rethinking reasoning with Masked Diffusion Models

A unified perspective on fine-tuning and sampling with diffusion and flow models

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

Value Gradient Guidance for Flow Matching Alignment

Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control

Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching

Conditioning Diffusions Using Malliavin Calculus