Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schrödinger Bridge Matching

Jeongwoo Shin; Jinhwan Sul; Joonseok Lee; Jaewong Choi; Jaemoo Choi

cs.CVFeb 17, 2026

Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schrödinger Bridge Matching

Authors: Jeongwoo Shin, Jinhwan Sul, Joonseok Lee, Jaewong Choi, Jaemoo Choi

Organizations: Seoul National University · Georgia Institute of Technology · Sungkyunkwan University

Abstract

Diffusion models often yield highly curved trajectories and noisy score targets due to an uninformative, memoryless forward process that induces independent data-noise coupling. We propose Adjoint Schrödinger Bridge Matching (ASBM), a generative modeling framework that recovers optimal trajectories in high dimensions via two stages. First, we view the Schrödinger Bridge (SB) forward dynamic as a coupling construction problem and learn it through a data-to-energy sampling perspective that transports data to an energy-defined prior. Then, we learn the backward generative dynamic with a simple matching loss supervised by the induced optimal coupling. By operating in a non-memoryless regime, ASBM produces significantly straighter and more efficient sampling paths. Compared to prior works, ASBM scales to high-dimensional data with notably improved stability and efficiency. Extensive experiments on image generation show that ASBM improves fidelity with fewer sampling steps. We further showcase the effectiveness of our optimal trajectory via distillation to a one-step generator.

Figures & tables

Panel of Figure 1 — Figure 1 : Generation trajectory of score matching and ASBM. Top : Backward drift accumulated over time in pixel level. Bottom : Denoising path in image level. ASBM shows significantly smaller transport cost with straighter path, leading to efficient generation.

Figure 2 : Generated samples from ASBM on pixel space (CIFAR-10) and on latent space (FFHQ).

Method	OC	No PT	FB	FID $\downarrow$
Refinement method
DOT ( Tanaka, 2019 )	✓	✗	–	15.78
DGFLOW ( Ansari et al., 2021 )	✓	✗	–	9.63
Flow-based method
FM ( Lipman et al., 2023 )	✗	✓	✓	6.35
Rectified Flow ( Liu et al., 2023b )	✓	✓	✗	6.01

Table 1 : FID evaluation on CIFAR-10. ASBM shows superior generative performance by achieving all three key advantages: optimal coupling (OC), no reliance on pre-training (No PT), and consistent forward–backward dynamics (FB).

Figure 3 : FID comparison along the NFE. We use M and NM to denote the memoryless and non-memoryless condition, respectively. BM denotes empirical bridge-matching pretraining.

NFE	25	50	100	250	500	1000
Score SDE	52.08	19.02	9.84	7.79	6.88	6.63
ASBM (Ours)	8.85	7.64	6.85	6.47	6.38	6.27

Table 2 : FID evaluation on latent space of FFHQ.

Panel of Figure 4 — Figure 4 : Trajectory efficiency. Left : Ours shows significantly straighter trajectory, leading to low NFE at generation. Right : Ours has lower trajectory variance, implying its better organized path.

Method	Score SDE	SB-FBSDE	DSBM	ASBM
FID	6.72	285.77	39.84	3.74

Table 3 : FID at 25 steps with Heun solver on CIFAR-10.

Figure 5 : Localized prior-data coupling. ASBM trajectories preserve information: reversing from a noised image produces samples similar to the original. In contrast, memoryless dynamics yield completely random samples due to highly noisy trajectories.

Figure 6 : Uncurated one-step generation from distillation on CIFAR-10 . Red boxes highlight repeated patterns indicating mode collapse. DMD still suffers from mode collapse despite the costly regression loss, whereas ASBM achieves diverse generation due to its organized, localized coupling.

Method	FID $\downarrow$	Recall $\uparrow$	Precision $\uparrow$
SDS ( Poole et al., 2023 )	9.36	0.504	0.706
DMD ( Yin et al., 2024b )	8.25	0.513	0.715
Ours	6.68	0.542	0.702

Table 4 : Result of distillation to one-step generator on CIFAR-10.

Figure 7 : Initialization of one-step generator on CIFAR-10. Diffusion-based initialization (left) produces noisy images even with timestep shifting, while ASBM (right) yields clear initial estimates due to its straighter and more organized trajectory

Figure 8 : Ablation on different degree of memorylessness.

Forward	Backward NFE
NFE	25	50	100	250	500	1000
10	23.62	8.03	3.58	3.40	3.28	3.05
20	20.83	5.39	3.05	2.91	2.87	2.74
50	20.73	5.87	3.16	3.01	2.94	2.77

Table 5 : Ablation on different forward NFE.

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Figure I : Initialization of one-step generator (Uncurated generation). As discussed in Sec. 3.3 , ASBM shows clear initialization for one-step generator, indicating its straighter and more organized trajectory. On the other hand, score-based initialization gives much more noisy initialization even with timestep shifting ( Yin et al., 2024b ) .

Figure II : Mode collapse in distillation (Uncurated generation). ASBM shows strong mode coverage in distillation task while the score distillation models still suffer from mode collapse even with costly regression loss.

	Scalar (mean, var)	$\\|X_{1}\\|_{2}^{2}$ (mean, var)	Eigenvalues (min, max)
Gaussian reference	$(0,\;1)$	$(3072,\;6144)$	$(0.566,\;1.557)$
ASBM (learned forward)	$(-0.001,\;1.012)$	$(3090,\;6322)$	$(0.572,\;1.594)$

Appendix

Table I : Prior alignment diagnostics on CIFAR-10. Each metric compares

N{=}50\text{K}

forward-simulated samples against true Gaussian samples of the same size (

D{=}3072

Explore similar work

Reflected Schrödinger Bridge Matching
Jul 3, 2026Marcus Häggbom, Viktor Nilsson, Pierre Nyquist +1Schrödinger Bridges Generative Models
SEB Group and Department of Mathematics KTH Royal Institute of Technology Stockholm, Sweden · Department of Mathematical Sciences Chalmers University of Technology and University of Gothenburg and Department of Mathematics KTH Royal Institute of Technology
Notes on generative modeling: flow matching, diffusion, optimal transport and Schr{ö}dinger bridge
Jun 29, 2026Titouan VayerSchrödinger Bridges Generative Models
COMPACT · Inria, Rennes, France.
Twisted Schrödinger Bridge Matching
Jul 18, 2026Maxence Noble, Marie Scheid, Yazid Janati +2Schrödinger Bridges Differentiable Optimal Transport
CMAP, Ecole polytechnique · Institute of Foundation Models · MBZUAI +1

Jul 3, 2026, cs.LGJ/K move · Enter open · S save

Reflected Schrödinger Bridge Matching

Marcus Häggbom, Viktor Nilsson, Pierre Nyquist, Joakim andén

SEB Group and Department of Mathematics KTH Royal Institute of Technology Stockholm, Sweden · Department of Mathematical Sciences Chalmers University of Technology and University of Gothenburg and Department of Mathematics KTH Royal Institute of Technology

Schrödinger Bridges Generative Models Implicit Differentiation

Open paper AskPDF arXiv

Recent advances in generative modeling have enabled the efficient computation of Schrödinger bridges (SB) in high-dimensional settings by leveraging partially simulation-free training methods inspired by flow matching. However, these have not covered SBs with reflecting dynamics, a useful model choice with built-in guarantees that generated samples stay in the data domain. Existing alternatives for reflected SBs instead rely on more complex training based on forward--backward SDE theory, requiring expensive higher-order derivatives and sampling entire paths during training. In this article, we introduce a partially simulation-free framework that allows reflected SBs to be trained similarly to flow matching, using a new sampling method and regression target. We demonstrate our results by coupling pairs of well-known high-dimensional image datasets. Using reflected dynamics incurs negligible additional wall-clock time during both training and inference while maintaining or slightly improving generative performance.

Abstract

Explore similar work

Reflected Schrödinger Bridge Matching

Notes on generative modeling: flow matching, diffusion, optimal transport and Schr{ö}dinger bridge

Twisted Schrödinger Bridge Matching