arXiv Computer Vision
Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schr\"odinger Bridge Matching
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Jul 7
Reflected Schr\"odinger Bridge Matching
arXiv:2607. 03626v1 Announce Type: new Abstract: Recent advances in generative modeling have enabled the efficient computation of Schr\"odinger bridges (SB) in high-dimensional settings by leveraging partially simulation-free training methods inspired by flow matching.
arXiv Computer Vision
Aug 25
Bridging Restoration and Generation in One-step Diffusion for Real-World Image Super-Resolution
arXiv:2604.24136v3 Announce Type: replace Abstract: Pretrained diffusion models have revolutionized real-world image super-resolution (Real-ISR), but their iterative sampling is computationally prohi...
arXiv Machine Learning
Sep 1
Data-to-Energy Stochastic Dynamics
arXiv:2509.26364v3 Announce Type: replace Abstract: The Schr\"odinger bridge problem is concerned with finding a stochastic dynamical system bridging two marginal distributions that minimises a certa...
arXiv Machine Learning
Jun 4
Optimal Transport Flow Matching by Design
arXiv:2606. 04092v1 Announce Type: cross Abstract: Flow matching models learn to transport samples from a simple prior distribution to a complex data distribution.
Hugging Face Trending Papers
Jun 29
UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception
Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches typically treat diffusion-based controllable generation and dense prediction as separate tasks, overlooking the potential benefits of jointly modeling the heterogeneous distributions.
arXiv Machine Learning
Sep 17
Beyond Random Couplings: Contrastive Noise Alignment in Generative Flows
The paper introduces Contrastive Noise Alignment (CNA), a training-time method for generative flow models that dynamically aligns Gaussian noise with data samples using a cross-modal InfoNCE objective. By modeling noise as an interacting particle system and regularizing with angular entropy and radial norm penalties, CNA reduces arbitrary data-noise couplings and flow curvature. Empirical results show that CNA improves generation quality, lowering FID by over 50% for few-step pixel-space generation compared to standard rectified flow and outperforming optimal transport baselines by at least 24%.