A hybrid image generator that uses an autoregressive transformer as an encoder and a diffusion model as a decoder reaches FID 1.42 on ImageNet 256x256, with an iterative multi-reference mode that improves quality over one-shot generation.
The euler scheme for stochastic differential equations: error analysis with malliavin calculus
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Marrying Autoregressive Transformer and Diffusion with Multi-Reference Autoregression
A hybrid image generator that uses an autoregressive transformer as an encoder and a diffusion model as a decoder reaches FID 1.42 on ImageNet 256x256, with an iterative multi-reference mode that improves quality over one-shot generation.