SPAE compresses pretrained vision latents into a 64-channel bottleneck with channel-wise masking, improving image generation while keeping reconstruction and semantic understanding strong.
The Fourteenth International Conference on Learning Representations , year=
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
-
SPAE: Spectrally Guided Autoencoder for Pretrained Visual Latents
SPAE compresses pretrained vision latents into a 64-channel bottleneck with channel-wise masking, improving image generation while keeping reconstruction and semantic understanding strong.