1 citations · 1 across the 12 of their papers we have counts for
14 papers
Beckmann Transport Models: From Autonomous Flows to One-Step Maps
Lee Cheuk-Kit, Florentin Coeurdoux, Yuyuan Chen +5
We propose an instantiation of flow matching that relies on a time-independent velocity field (an \emph{autonomous flow}) to exactly map between two distributions, so long as the t…
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…
Discrete Tilt Matching
Yuyuan Chen, Shiyi Wang, Peter Potaptchik +2
Masked diffusion large language models (dLLMs) are a promising alternative to autoregressive generation. While reinforcement learning (RL) methods have recently been adapted to dLL…
Discrete Flow Maps
Peter Potaptchik, Jason Yim, Adhi Saravanan +3
The sequential nature of autoregressive next-token prediction imposes a fundamental speed limit on large language models. While continuous flow models offer a path to parallel gene…
Meta Flow Maps enable scalable reward alignment
Peter Potaptchik, Adhi Saravanan, Abbas Mammadov +3
Controlling generative models is computationally expensive. This is because optimal alignment with a reward function--whether via inference-time steering or fine-tuning--requires e…
Tilt Matching for Scalable Sampling and Fine-Tuning
Peter Potaptchik, Cheuk-Kit Lee, Michael S. Albergo
We propose a simple, scalable algorithm for using stochastic interpolants to sample from unnormalized densities and for fine-tuning generative models. The approach, Tilt Matching,…
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…
CREPE: Controlling Diffusion with Replica Exchange
Jiajun He, Paul Jeha, Peter Potaptchik +5
Inference-time control of diffusion models aims to steer model outputs to satisfy new constraints without retraining. Previous approaches have mostly relied on heuristic guidance o…
Schrödinger Bridge Matching for Tree-Structured Costs and Entropic Wasserstein Barycentres
Samuel Howard, Peter Potaptchik, George Deligiannidis
Recent advances in flow-based generative modelling have provided scalable methods for computing the Schrödinger Bridge (SB) between distributions, a dynamic form of entropy-regular…
Adaptive Diffusion Guidance via Stochastic Optimal Control
Iskander Azangulov, Peter Potaptchik, Qinyu Li +3
Guidance is a cornerstone of modern diffusion models, playing a pivotal role in conditional generation and enhancing the quality of unconditional samples. However, current approach…
Accelerated Parallel Tempering via Neural Transports
Leo Zhang, Peter Potaptchik, Jiajun He +5
Markov Chain Monte Carlo (MCMC) algorithms are essential tools in computational statistics for sampling from unnormalised probability distributions, but can be fragile when targeti…
Linear Convergence of Diffusion Models Under the Manifold Hypothesis
Peter Potaptchik, Iskander Azangulov, George Deligiannidis
Score-matching generative models have proven successful at sampling from complex high-dimensional data distributions. In many applications, this distribution is believed to concent…
Metric Flow Matching for Smooth Interpolations on the Data Manifold
Kacper Kapuśniak, Peter Potaptchik, Teodora Reu +5
Matching objectives underpin the success of modern generative models and rely on constructing conditional paths that transform a source distribution into a target distribution. Des…
de Finetti's theorem and the existence of regular conditional distributions and strong laws on exchangeable algebras
Peter Potaptchik, Daniel M. Roy, David Schrittesser
We show the following generalizations of the de Finetti--Hewitt--Savage theorem: Given an exchangeable sequence of random elements, the sequence is conditionally i.i.d. if and only…