activity
20242026
collaborators

9 papers

cs.LG2026

Why Are DMD Students Lazy? Understanding the Copying Behavior in Few-Step Distillation

Shucheng Li, Iolo Jones, Alexander Tong +1

Distribution Matching Distillation (DMD) compresses pretrained diffusion models into efficient few-step generators by aligning their noised distributions across all scales. In prin…

cs.LG2026

Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schrödinger Samplers

Bruno Trentini, Dejan Stancevic, Michael M. Bronstein +2

For a fixed flow-based generative model under a small inference budget, sample quality can depend strongly on where the sampler spends its few function evaluations. Flow matching a…

cs.LG2026

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

Emily Jin, Andrei Cristian Nica, Mikhail Galkin +8

Accurately predicting experimentally realizable 3D molecular crystal structures from their 2D chemical graphs is a long-standing open challenge in computational chemistry called cr…

cs.LG2026

Planner Aware Path Learning in Diffusion Language Models Training

Fred Zhangzhi Peng, Zachary Bezemek, Jarrid Rector-Brooks +5

Diffusion language models have emerged as a powerful alternative to autoregressive models, enabling fast inference through more flexible and parallel generation paths. This flexibi…

cs.LG2026

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

Oscar Davis, Michael S. Albergo, Nicholas M. Boffi +2

Geometric data and purpose-built generative models on them have become ubiquitous in high-impact deep learning application domains, ranging from protein backbone generation and com…

cs.LG2026

Amortized Sampling with Transferable Normalizing Flows

Charlie B. Tan, Majdi Hassan, Leon Klein +5

Efficient equilibrium sampling of molecular conformations remains a core challenge in computational chemistry and statistical inference. Classical approaches such as molecular dyna…