Saved in:
Bibliographic Details
Main Authors: Sabour, Amirmojtaba, Albergo, Michael S., Domingo-Enrich, Carles, Boffi, Nicholas M., Fidler, Sanja, Kreis, Karsten, Vanden-Eijnden, Eric
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.22688
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908679755792384
author Sabour, Amirmojtaba
Albergo, Michael S.
Domingo-Enrich, Carles
Boffi, Nicholas M.
Fidler, Sanja
Kreis, Karsten
Vanden-Eijnden, Eric
author_facet Sabour, Amirmojtaba
Albergo, Michael S.
Domingo-Enrich, Carles
Boffi, Nicholas M.
Fidler, Sanja
Kreis, Karsten
Vanden-Eijnden, Eric
contents A common recipe to improve diffusion models at test-time so that samples score highly against a user-specified reward is to introduce the gradient of the reward into the dynamics of the diffusion itself. This procedure is often ill posed, as user-specified rewards are usually only well defined on the data distribution at the end of generation. While common workarounds to this problem are to use a denoiser to estimate what a sample would have been at the end of generation, we propose a simple solution to this problem by working directly with a flow map. By exploiting a relationship between the flow map and velocity field governing the instantaneous transport, we construct an algorithm, Flow Map Trajectory Tilting (FMTT), which provably performs better ascent on the reward than standard test-time methods involving the gradient of the reward. The approach can be used to either perform exact sampling via importance weighting or principled search that identifies local maximizers of the reward-tilted distribution. We demonstrate the efficacy of our approach against other look-ahead techniques, and show how the flow map enables engagement with complicated reward functions that make possible new forms of image editing, e.g. by interfacing with vision language models.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22688
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Test-time scaling of diffusions with flow maps
Sabour, Amirmojtaba
Albergo, Michael S.
Domingo-Enrich, Carles
Boffi, Nicholas M.
Fidler, Sanja
Kreis, Karsten
Vanden-Eijnden, Eric
Machine Learning
Artificial Intelligence
A common recipe to improve diffusion models at test-time so that samples score highly against a user-specified reward is to introduce the gradient of the reward into the dynamics of the diffusion itself. This procedure is often ill posed, as user-specified rewards are usually only well defined on the data distribution at the end of generation. While common workarounds to this problem are to use a denoiser to estimate what a sample would have been at the end of generation, we propose a simple solution to this problem by working directly with a flow map. By exploiting a relationship between the flow map and velocity field governing the instantaneous transport, we construct an algorithm, Flow Map Trajectory Tilting (FMTT), which provably performs better ascent on the reward than standard test-time methods involving the gradient of the reward. The approach can be used to either perform exact sampling via importance weighting or principled search that identifies local maximizers of the reward-tilted distribution. We demonstrate the efficacy of our approach against other look-ahead techniques, and show how the flow map enables engagement with complicated reward functions that make possible new forms of image editing, e.g. by interfacing with vision language models.
title Test-time scaling of diffusions with flow maps
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.22688