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

arXiv:2609.11804 · cs.CV, cs.AI, cs.LG · Submitted 2026-09-10 · Read on arXiv

cs.CV, cs.AI, cs.LG

Submitted: 2026-09-10

Updated: 2026-09-10

Comments: ECCV 2026

Project page: https://compvis.github.io/logit-refiner

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Ablation — 1× in this paper · explained in 1 episode

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models