3 papers
math.PR2026
The Fenchel Game of Underdamped Langevin Dynamics: Insights into Accelerated Convergence
Alexandra Borkowski, Nikolas Nüsken
For governed by suitably damped underdamped Langevin dynamics, we quantify the convergence in KL divergence of the positional marginal to a -strongly log-concave tar…
stat.ML2026
A Mean-Field Framework for Inference-Time Distributional Control of Diffusion Models
Samuel Howard, Nikolas Nüsken
Diffusion models are increasingly used as controllable samplers, whose generations can be steered at inference time according to a chosen reward function. While such rewards are ty…
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…