arXiv:2609.03443v1 Announce Type: new Abstract: The performance of Flow Matching largely depends on the quality of the coupling between the source and target distributions. However, independent coupling often leads to path crossings and local velocity ambiguity, while OT-based co…
arXiv cs.LG
TIER_1English(EN)·Qinchan Li, Pedro Cisneros-Velarde, Keru Fu, Samuel Antunes Miranda, Sharan Vaswani, Hao Zhang·
arXiv:2609.01746v1 Announce Type: new Abstract: Flow Matching has emerged as a leading framework for generative modeling, powering state-of-the-art systems such as FLUX and Stable Diffusion 3.5. However, the iterative nature of its ODE-based sampling process creates a fundamental…
arXiv cs.AI
TIER_1English(EN)·Yeonwoo Cha, Jaehoon Yoo, Semin Kim, Yunseo Park, Jinhyeon Kwon, Seunghoon Hong·
arXiv:2604.04646v2 Announce Type: replace-cross Abstract: Flow-based models learn a target distribution by modeling a marginal velocity field, defined as the average of sample-wise velocities connecting each sample from a simple prior to the target data. When sample-wise velociti…
arXiv cs.LG
TIER_1English(EN)·Juliana Felder, Milad Habibi, Soheyl Massoudi, Mark Fuge·
arXiv:2609.00863v1 Announce Type: new Abstract: Engineering inverse design is often limited by the high computational cost of iterative solvers for optimization problems constrained by partial differential equations (PDEs) and by their sensitivity to initialization. Deep generati…
arXiv cs.AI
TIER_1English(EN)·Yuanyi Yan, Xinzhe Rao, Canyu Shen, Yang Chen, Yunlu Chen, Meng Tang, Teng Long, Vincent Tao Hu·
arXiv:2608.29160v1 Announce Type: cross Abstract: We aim to improve frozen flow-matching image generators by adding inference computation inside the denoiser, without changing model weights or the outer sampler. Existing generators usually spend extra test-time computation by inc…
arXiv:2510.01159v3 Announce Type: replace Abstract: Learning the dynamics of a process given sampled observations at several time points is an important but difficult task in many scientific applications. When no ground-truth trajectories are available, but one has only snapshots…
arXiv cs.CV
TIER_1English(EN)·Lucas Degeorge, Paul Couairon, Arijit Ghosh, Alexei A. Efros, David Picard, Vicky Kalogeiton·
arXiv:2609.02748v1 Announce Type: new Abstract: Natural images follow a $1/f^2$ spectral distribution: most signal energy lies in the low spatial frequencies, while the perceptually important structures such as textures and edges occupy sparse high-frequency bands. Pixel-space re…
arXiv cs.CV
TIER_1English(EN)·Baris Imre, Aram Salehi, Levente Baljer, Andrew Webb, Marius Staring, Efe Ilicak·
arXiv:2609.00960v1 Announce Type: new Abstract: Magnetic resonance images of the same subject look markedly different across field strengths, which complicates the comparison and pooling of data across sites. We address cross-field brain-MRI translation for the MRIxFields2026 cha…
arXiv:2609.00811v1 Announce Type: new Abstract: Flow Matching provides an efficient generative prior for image restoration by learning continuous transport between source and data distributions. However, existing methods typically incorporate measurement constraints through local…
arXiv:2609.00198v1 Announce Type: new Abstract: Modern explicit-time generative models, such as Flow Matching [Lipman et al., 2023] and Rectified Flow [Liu et al., 2023], are typically derived top-down via Optimal Transport and the continuity equation. This standard Eulerian appr…
