activity
20242026
collaborators
Showing stat.MLShow all

8 papers · 1 filter

stat.ML2026

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…

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…

stat.ML2026

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…

stat.ML2026

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…

stat.ML2026

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…

stat.ML2025

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,…