← Back to all news
arXiv Machine Learning By Md Sakib Hossain Shovon, Md Rifat Ur Rahman, Md Abtahi Majeed Chowdhury, Yunhong Min, Jaesik Choi, Minhyuk Sung

I-SplineFlow: Learning Monotone Spline Stochastic Interpolant Schedulers for Few-Step Generation

Read the original on arXiv Machine Learning →

I‑SplineFlow introduces a new way to learn monotone spline stochastic interpolant schedulers for few‑step generation with pretrained diffusion and flow models. By parameterizing the scheduler with integrated monotone splines (I‑splines), the method decouples polynomial degree from the number of mixture weights, enabling compact support, better‑conditioned Jacobians, and strictly monotone signal‑to‑noise ratios without ordering constraints. Experiments on EDM, ReFlow, and Simple ReFlow show that I‑SplineFlow consistently improves few‑step FID over Bézier scheduling, especially at low NFEs, while training in only minutes.

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 Computer Vision
Aug 24

Difficulty-Calibrated Interpolation Paths for Conditional Flow Matching

The paper introduces Difficulty-Calibrated Flow Matching, a method that adapts the noise-to-data interpolation schedule in Conditional Flow Matching based on a pilot run’s loss profile. By setting the schedule to the quantile function of this difficulty profile, the training trajectory spends more time where the velocity is hardest to learn. Experiments on CIFAR-10, MNIST, and Fashion‑MNIST show that this calibrated path achieves the best FID on CIFAR‑10 and outperforms all fixed schedules in large‑batch, few‑update settings, where compute is most limited.

By Airin Akter Tania, Md Raihan Khan
diffusion
More like this →
Hugging Face Trending Papers
Jul 13

Velocity Scheduled Flow Matching

Flow matching trains a neural network to regress the conditional velocity along a linear interpolant between noise and data, and the number of network evaluations~(NFE) sets the cost of sampling. The straight-line interpolant carries an implicit choice: the sample moves at constant speed throughout the trajectory.

diffusion
More like this →
arXiv Machine Learning
Jul 14

Velocity Scheduled Flow Matching

arXiv:2607. 11442v1 Announce Type: new Abstract: Flow matching trains a neural network to regress the conditional velocity along a linear interpolant between noise and data, and the number of network evaluations~(NFE) sets the cost of sampling.

By Vitalii Bondar
diffusion
More like this →