cd /news/artificial-intelligence/wait-for-the-signal-simple-frequency… · home topics artificial-intelligence article
[ARTICLE · art-84198] src=arxiv.org ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

WaiT for the Signal: Simple Frequency-Aware Flow-Matching

Researchers introduce WaiT, a Wavelet-aware image Transformer that decomposes image generation into coarse and fine bands via lossless wavelets, allowing high-frequency bands to remain pure noise until coarse structure emerges. On ImageNet 512x512, WaiT achieves a pixel-space FID of 1.43 and reduces sampling compute by up to 50%, and with its largest 2B model sets a new state-of-the-art FID of 1.3 for pixel-space models. The method also achieves a state-of-the-art FVD of 0.84 on Kinetics-600 for video generation.

read1 min views1 publishedAug 3, 2026

arXiv:2607.28760v1 Announce Type: new Abstract: As image generation models scale to ever higher resolutions, global coherence, local detail, and texture fidelity become critical axes for generation quality. However, standard flow matching treats all spatial frequencies uniformly, ignoring the natural frequency hierarchy where high-frequency bands become indistinguishable from pure noise far earlier than coarse structures. We introduce WaiT, a Wavelet-aware image Transformer that decomposes generation into coarse and fine bands via lossless wavelets. True to its name, the high-frequency bands wait for the signal: staying pure noise until coarse structure has emerged, then joining the flow for joint refinement. Since standard FID discards fine-grained detail through aggressive downsampling, we introduce a more stringent three-axis evaluation protocol to assess quality at native resolution. On ImageNet 512x512, WaiT achieves a pixel-space FID of 1.43 and is Pareto-optimal across all three axes, reducing sampling compute by up to 50%. With our largest 2B model, we set a new state-of-the-art FID of 1.3 for pixel-space models on ImageNet 512 resolution. Our formulation outperforms even the strongest latent-space models on texture fidelity, and scales seamlessly to high-resolution OpenImages and to video generation, achieving a state-of-the-art FVD of 0.84 on Kinetics-600 with no algorithmic modifications.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @wait 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/wait-for-the-signal-…] indexed:0 read:1min 2026-08-03 ·