FREPix achieves competitive FID scores on ImageNet by decomposing image generation into separate low- and high-frequency paths within a flow matching framework.
Representation alignment for generation: Training diffusion transformers is easier than you think
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generation
FREPix achieves competitive FID scores on ImageNet by decomposing image generation into separate low- and high-frequency paths within a flow matching framework.