Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling
The Logit Refiner is introduced, a lightweight autoregressive module that restores intra-scale dependencies by sequentially sampling tokens conditioned on frozen backbone features and generalizes to text-to-image generation, confirming that the mean-field bottleneck persists across VAR variants and is effectively allev...
Meimingwei Li, S. Baumann, F. Krause et al.
· 0 citations