SOURCE-LINKED INTELLIGENCE

Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Visual Autoregressive Models (VAR) generate images through next-scale prediction, producing all tokens within each scale in parallel. We show that this parallel decoding constitutes a mean-field-style approximation that discards spatial dependencies among same-scale tokens, causing locally incoherent samples regardless of backbone capacity -- a limitation of the decoding rule. Addressing this limitation, we introduce the Logit Refiner, a lightweight autoregressive module that restores intra-scale dependencies by sequentially sampling tokens conditioned on frozen backbone features. Adding only

Read original source ↗ Open in workspace

recordType

paper

region

Global