activity
20242026
collaborators

9 papers

stat.ML2026

Itô maps for any-step SDEs

Zhengkai Pan, Peter Potaptchik, Wenxi Yao +2

Recent one-step generative models accelerate sampling by learning deterministic flow maps of the underlying dynamics. These methods rely on learning from ordinary differential equa…

cs.LG2026

Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models

Andreas Bergmeister, Stefanie Jegelka, Nikolas Nüsken +2

Diffusion and flow-matching models scale because pretraining is supervised regression: a clean sample is noised analytically, and a model regresses against a closed-form target. RL…

stat.ML2026

Control Consistency Losses for Diffusion Bridges

Samuel Howard, Nikolas Nüsken, Jakiw Pidstrigach

Simulating the conditioned dynamics of diffusion processes, given their initial and terminal states, is an important but challenging problem in the sciences. The difficulty is part…

cs.LG2025

Sensitivity Analysis for Climate Science with Generative Flow Models

Alex Dobra, Jakiw Pidstrigach, Tim Reichelt +6

Sensitivity analysis is a cornerstone of climate science, essential for understanding phenomena ranging from storm intensity to long-term climate feedbacks. However, computing thes…

cs.LG2025

Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive

Tyler Farghly, Peter Potaptchik, Samuel Howard +2

Diffusion models have achieved state-of-the-art performance, demonstrating remarkable generalisation capabilities across diverse domains. However, the mechanisms underpinning these…

stat.ML2025

Conditioning Diffusions Using Malliavin Calculus

Jakiw Pidstrigach, Elizabeth Baker, Carles Domingo-Enrich +2

In generative modelling and stochastic optimal control, a central computational task is to modify a reference diffusion process to maximise a given terminal-time reward. Most exist…