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

Abstract

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 ~10% parameters and less than 5% of the base model's training compute, it plugs into any pretrained VAR checkpoint without retraining. Controlled ablations isolate joint intra-scale sampling -- rather than additional capacity or training -- as the critical ingredient. Across backbones from 310M to 2B parameters on class-conditional ImageNet 256x256, the refiner consistently improves generation quality, enabling a 1.1B-parameter model to surpass one twice its size. The approach further generalizes to text-to-image generation, confirming that the mean-field bottleneck persists across VAR variants and is effectively alleviated by our method. Project page: https://compvis.github.io/logit-refiner/

Authors 4

Meimingwei Li, Stefan Andreas Baumann, Felix Krause, Bj\"orn Ommer

Specification

Official page: arxiv.org/abs/2609.11804
Source:arXiv (Atom API + RSS)T1observed 50 min agohigh
Arxiv announce type: new
Source:arXiv (Atom API + RSS)T1observed 49 min agohigh
arXiv id: 2609.11804
Source:arXiv (Atom API + RSS)T1observed 50 min agohigh
Categories: cs.CV, cs.AI, cs.LG
Source:arXiv (Atom API + RSS)T1observed 50 min agohigh
PDF: arxiv.org/pdf/2609.11804
Source:arXiv (Atom API + RSS)T1observed 50 min agohigh
Primary category: cs.CV
Source:arXiv (Atom API + RSS)T1observed 50 min agohigh
Published: 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

49 min ago

Conflicts

None

No models linked to this paper yet.

Authors: Meimingwei Li, Stefan Andreas Baumann, Felix Krause

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Abstract

1 claims · 1 propertiesShow all properties

Abstractabstract1

Claim history for Abstract
Value	Valid from → to	Status	Source	Confidence	Extractor
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 ~10% parameters and less than 5% of the base model's training compute, it plugs into any pretrained VAR checkpoint without retraining. Controlled ablations isolate joint intra-scale sampling -- rather than additional capacity or training -- as the critical ingredient. Across backbones from 310M to 2B parameters on class-conditional ImageNet 256x256, the refiner consistently improves generation quality, enabling a 1.1B-parameter model to surpass one twice its size. The approach further generalizes to text-to-image generation, confirming that the mean-field bottleneck persists across VAR variants and is effectively alleviated by our method. Project page: https://compvis.github.io/logit-refiner/	11 Sept 2026 21:02 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
Property changedPaperLogit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling
Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling: arxiv announce type changed from cross to new
Arxiv announce typecross→newarxiv
rss.arxiv.org
11 Sept 2026
New paperPaperLogit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling
New paper: Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling
arxiv
rss.arxiv.org

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.CV	feed	T1· Official	49 min ago	1
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.LG	feed	T1· Official	50 min ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.