# Learning When to Denoise: Optimizing Asynchronous Schedules for Latent Diffusion

Source: [Learning When to Denoise: Optimizing Asynchronous Schedules for Latent Diffusion](<https://www.sota2.com/research/paper/6a34ccf1206542251d7c5e2e>)

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

Data updated: 2026-06-20T05:00:05.764Z

Authors: Bingshuo Qian, Xiang Cheng

Published: 2026-06-18T00:13:42.000Z

## Abstract

Multi-representation diffusion models can improve visual synthesis by denoising complementary views of an image, but their performance depends critically on the asynchronous schedule that determines when each representation is denoised. We propose to learn this schedule. Our method formulates asynchronous flow matching over multiple representation spaces and uses a schedule-corrected objective that keeps each representation's local noising-time weights fixed as the schedule changes. We instantiate the schedule with a flexible parametric class that is convex and monotone by construction, and learn it using a fast joint probe with less than 1% additional training compute. On ImageNet 256x256, the learned schedule substantially improves both convergence speed and final quality under a matched 675M-parameter XL backbone. With AutoGuidance, our 200-epoch model reaches FID 1.05, matching the 800-epoch SFD-XL baseline with 4x less training. Training to 600 epochs further improves to FID 1.02, outperforming the 1B-parameter SFD-XXL result of FID 1.04 while using a smaller model. In the unguided setting, our 200-epoch model reaches FID 2.37, already below the best 800-epoch SFD-XL result (2.54) at 4x less training, and improves to FID 2.14 at 600 epochs. Code is available at https://github.com/bsq532087/LWD

## 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.

- [Class-conditional Image Generation on ImageNet 256x256](<https://www.sota2.com/research/sota/class-conditional-image-generation-on-imagenet-256x256.md>): Class-conditional Image Generation; ImageNet 256x256; Inception Score (IS): 273.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.19662>)

[PDF](<https://arxiv.org/pdf/2606.19662.pdf>)
