papers
Publications (14)
stat.ML2025
Linear Convergence of Diffusion Models Under the Manifold Hypothesis
Peter Potaptchik, Iskander Azangulov, George Deligiannidis
stat.ML2025
Tilt Matching for Scalable Sampling and Fine-Tuning
Peter Potaptchik, Cheuk-Kit Lee, Michael S. Albergo
stat.ML2026
Adaptive Diffusion Guidance via Stochastic Optimal Control
Iskander Azangulov, Peter Potaptchik, Qinyu Li +3
stat.ML2026
Itô maps for any-step SDEs
Zhengkai Pan, Peter Potaptchik, Wenxi Yao +2
cs.LG2026
Beckmann Transport Models: From Autonomous Flows to One-Step Maps
Lee Cheuk-Kit, Florentin Coeurdoux, Peter Potaptchik +3
cs.LG2026
CREPE: Controlling Diffusion with Replica Exchange
Jiajun He, Paul Jeha, Peter Potaptchik +5
stat.ML2026
Discrete Flow Maps
Peter Potaptchik, Jason Yim, Adhi Saravanan +3
math.PR2023
de Finetti's theorem and the existence of regular conditional distributions and strong laws on exchangeable algebras
Peter Potaptchik, Daniel M. Roy, David Schrittesser
cs.LG2026
Discrete Tilt Matching
Yuyuan Chen, Shiyi Wang, Peter Potaptchik +2
cs.LG2025
Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive
Tyler Farghly, Peter Potaptchik, Samuel Howard +2
cs.LG2024
Metric Flow Matching for Smooth Interpolations on the Data Manifold
Kacper KapuÅniak, Peter Potaptchik, Teodora Reu +5
stat.ML2026
Accelerated Parallel Tempering via Neural Transports
Leo Zhang, Peter Potaptchik, Jiajun He +5
stat.ML2026
Meta Flow Maps enable scalable reward alignment
Peter Potaptchik, Adhi Saravanan, Abbas Mammadov +3
stat.ML2025
Schrödinger Bridge Matching for Tree-Structured Costs and Entropic Wasserstein Barycentres
Samuel Howard, Peter Potaptchik, George Deligiannidis