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: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: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:2606. 04092v1 Announce Type: cross Abstract: Flow matching models learn to transport samples from a simple prior distribution to a complex data distribution.
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.
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%.
arXiv:2606. 02453v1 Announce Type: cross Abstract: Despite the remarkable fidelity of generative models, they frequently suffer from mode collapse.
arXiv:2506. 13058v2 Announce Type: replace-cross Abstract: Diffusion probabilistic models (DPMs) have demonstrated remarkable success in visual generation.
arXiv:2607. 19332v1 Announce Type: new Abstract: Generative models have undergone many generations of evolution, from VAEs/GANs to diffusion/flow matching.
arXiv:2606. 11156v1 Announce Type: cross Abstract: Recent one-step generative models accelerate sampling by learning deterministic flow maps of the underlying dynamics.
Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and fine-grained details in a high-dimensional space. Standard flow matching interpolates noise toward a fixed clean-image endpoint, leaving the spectral evolution to be learned implicitly.
arXiv:2502. 10389v2 Announce Type: replace-cross Abstract: Diffusion models (DMs) have become the leading choice for generative tasks across diverse domains.