PaperScope
LIVE · 2026-09-29 05:40 UTC

Tilted Schrödinger Bridge Matching

Sergei Kholkin, Evgeny Burnaev, Alexander Korotin

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.34642 v1
Category
Submitted
2026-09-28

Abstract

Schrödinger bridges provide an entropy-regularized framework and a principled solution for unpaired domain translation. In practice, a pretrained bridge may need to be adapted to human preferences or physical constraints through a reward a problem closely related to reward tilting in diffusion models but underexplored for Schrödinger bridges. We introduce Tilted Schrödinger Bridge Matching (TSBM), a post-training method for fine-tuning a learned bridge $P$ between source $p_0$ and target $p_1$ toward a reward-tilted target $p_1^r\propto p_1e^r$, while preserving source $p_0$. We formulate this adaptation as alternating optimization initialized from $P$, provide theoretical justification, and derive a practical algorithm based on Adjoint Matching. We evaluate TSBM on unpaired image-to-image translation targeting digit properties in MNIST and facial attributes in CelebA.

arXiv abs page · PDF · same-day batch