# ODE$\_t$(ODE$\_l$): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling

Source: [ODE$\_t$(ODE$\_l$): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling](<https://www.sota2.com/research/paper/68fa79c61e209131cea7f4df>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-20T05:01:37.411Z

Authors: Denis Gudovskiy, Wenzhao Zheng, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer

Published: 2025-06-26T18:59:59.000Z

## Abstract

Continuous normalizing flows (CNFs) and diffusion models (DMs) generate high-quality data from a noise distribution. However, their sampling process demands multiple iterations to solve an ordinary differential equation (ODE) with high computational complexity. State-of-the-art methods focus on reducing the number of discrete time steps during sampling to improve efficiency. In this work, we explore a complementary direction in which the quality-complexity tradeoff can also be controlled in terms of the neural network length. We achieve this by rewiring the blocks in the transformer-based architecture to solve an inner discretized ODE w.r.t. its depth. Then, we apply a length consistency term during flow matching training, and as a result, the sampling can be performed with an arbitrary number of time steps and transformer blocks. Unlike others, our ODE$\_t$(ODE$\_l$) approach is solver-agnostic in time dimension and reduces both latency and, importantly, memory usage. CelebA-HQ and ImageNet generation experiments show a latency reduction of up to $2\\times$ in the most efficient sampling mode, and FID improvement of up to $2.8$ points for high-quality sampling when applied to prior methods. We open-source our code and checkpoints at github.com/gudovskiy/odelt.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2506.21714>)

[PDF](<https://arxiv.org/pdf/2506.21714.pdf>)
