UDT, a U-Net diffusion transformer with data-adaptive token merging for down/upsampling, improves ImageNet generation FID while cutting training epochs from 1400 to 40 compared with SiT-XL.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction
UDT, a U-Net diffusion transformer with data-adaptive token merging for down/upsampling, improves ImageNet generation FID while cutting training epochs from 1400 to 40 compared with SiT-XL.