Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schrodinger Bridge Matching

arXiv:2602.15396v2 Announce Type: replace 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 Schrodinger Bridge Matching (ASBM), a generative modeling framework that recovers optimal trajectories in high dimensions via two stages. First, we view the Schrodinger 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.

Related

• Exploring Time Conditioning in Diffusion Generative Models from Disjoint Noisy Data Manifolds
• Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution
• Breaking the Curse of Dimensionality: Diffusion Models Efficiently Learn Low-Dimensional Distributions
• On the spectral properties of generative denoiser Jacobians

Source: arXiv cs.CV | 2026-10-02