DecQ uses detail-condensing queries on shallow and deep VFM features to improve both reconstruction PSNR and generative convergence/FID in RAEs without fine-tuning the encoder.
What matters for representation alignment: Global information or spatial struc- ture? InICLR, 2026
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
-
DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders
DecQ uses detail-condensing queries on shallow and deep VFM features to improve both reconstruction PSNR and generative convergence/FID in RAEs without fine-tuning the encoder.