Prologue adds a small set of learnable tokens trained exclusively with AR cross-entropy loss to decouple generation from reconstruction in autoregressive visual models, yielding lower gFID on ImageNet 256x256.
Soundstream: An end-to-end neural audio codec.IEEE ACM Trans
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Autoregressive Visual Generation Needs a Prologue
Prologue adds a small set of learnable tokens trained exclusively with AR cross-entropy loss to decouple generation from reconstruction in autoregressive visual models, yielding lower gFID on ImageNet 256x256.