2 papers
cs.CV2025
From Sequential to Spatial: Reordering Autoregression for Efficient Visual Generation
Siyang Wang, Hanting Li, Wei Li +3
Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token…
cs.CV2025
Navigating Image Restoration with VAR's Distribution Alignment Prior
Siyang Wang, Feng Zhao
Generative models trained on extensive high-quality datasets effectively capture the structural and statistical properties of clean images, rendering them powerful priors for trans…