← Back to all news
arXiv Machine Learning By Qinchan Li, Pedro Cisneros-Velarde, Keru Fu, Samuel Antunes Miranda, Sharan Vaswani, Hao Zhang

CAT-Flow: Curvature-Adaptive sTeps for Flow Matching

Read the original on arXiv Machine Learning →

The paper introduces CAT-Flow, a pair of lightweight, training‑free algorithms—CAT‑OV and CAT‑OT—that adapt step‑sizes during Flow Matching inference by estimating curvature in time or state space. These methods avoid extra neural evaluations and achieve constant‑order truncation error bounds. Experiments show that CAT‑OV and CAT‑OT improve image quality metrics across four text‑to‑image Flow Matching models, cutting the required generation steps by up to 40%.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jun 2

Low-Pass Flow Matching

arXiv:2606. 02177v1 Announce Type: new Abstract: Flow Matching typically relies on white noise sources, a choice often misaligned with the power spectra of natural data, which tend to decay with frequency.

By Francesco M. Ruscio, T. Konstantin Rusch
diffusionsafety
More like this →
arXiv AI
Sep 2

Training-Free Refinement of Flow Matching with Divergence-based Sampling

The paper introduces Flow Divergence Sampler (FDS), a training‑free method that refines intermediate states in flow‑matching models by using the divergence of the marginal velocity field to detect and correct misguidance toward low‑density regions. FDS operates during inference, requires no additional training, and can be applied as a plug‑and‑play module with standard solvers and existing flow backbones. Experiments show that FDS consistently improves fidelity in tasks such as text‑to‑image synthesis and inverse problems.

By Yeonwoo Cha, Jaehoon Yoo, Semin Kim, Yunseo Park, Jinhyeon Kwon, Seunghoon Hong
diffusion
More like this →