LOCUS: Causal Support Windows for Attribute Control in Autoregressive Image Generation

Unified autoregressive (AR) image generators struggle to satisfy multiple attribute constraints in a single prompt. Although these attributes are decodable from image-token latents, editing those latents at test time remains difficult. Adding a fixed attribute direction to the prefix can reinforce a requested attribute but rarely overrides a conflicting one, such as turning a car red when the prompt specifies blue. We investigate how the effect of an intervention depends on where it acts in the image-token sequence. We introduce the causal support profile, which measures, for each attribute, how often patching image-token states within a given window flips the rendered attribute. Structural attributes (count and position) are most responsive in early, narrow windows, while appearance attributes (color, size, and material) respond over later, broader windows. A budget-matched comparison of early and middle windows shows that the effect of window location depends on the target attribute, and two-dimensional support maps show that the responsive regions track spatial content. Based on these profiles, we propose LOCUS (Latent Optimization in Causal Support windows), which diagnoses which attribute failed and routes test-time latent optimization to its corresponding support window. With the generator, optimizer, reward, verifier, and token budget held fixed, support-routed windows outperform late windows by 23.6 percentage points in GenEval++ macro accuracy. With the generator frozen, LOCUS raises Janus-Pro's GenEval++ accuracy from 24.6% to 46.8% overall and from 19.5% to 40.5% on multi-attribute tags. On GenEval, LOCUS repairs 48.1% of failed generations in one rollout, compared with 37.4% for prefix optimization, and needs 14% fewer rounds on average to succeed.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-17
DOI
https://doi.org/10.48550/arxiv.2611.22867
Primary Topic
Generative Adversarial Networks and Image Synthesis
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

LOCUS: Causal Support Windows for Attribute Control in Autoregressive Image Generation

Zijun Huang
arXiv (Cornell University)
Generative Adversarial Networks and Image Synthesis
preprint

LOCUS: Causal Support Windows for Attribute Control in Autoregressive Image Generation

Zijun Huang
preprint en

Abstract

Unified autoregressive (AR) image generators struggle to satisfy multiple attribute constraints in a single prompt. Although these attributes are decodable from image-token latents, editing those latents at test time remains difficult. Adding a fixed attribute direction to the prefix can reinforce a requested attribute but rarely overrides a conflicting one, such as turning a car red when the prompt specifies blue. We investigate how the effect of an intervention depends on where it acts in the image-token sequence. We introduce the causal support profile, which measures, for each attribute, how often patching image-token states within a given window flips the rendered attribute. Structural attributes (count and position) are most responsive in early, narrow windows, while appearance attributes (color, size, and material) respond over later, broader windows. A budget-matched comparison of early and middle windows shows that the effect of window location depends on the target attribute, and two-dimensional support maps show that the responsive regions track spatial content. Based on these profiles, we propose LOCUS (Latent Optimization in Causal Support windows), which diagnoses which attribute failed and routes test-time latent optimization to its corresponding support window. With the generator, optimizer, reward, verifier, and token budget held fixed, support-routed windows outperform late windows by 23.6 percentage points in GenEval++ macro accuracy. With the generator frozen, LOCUS raises Janus-Pro's GenEval++ accuracy from 24.6% to 46.8% overall and from 19.5% to 40.5% on multi-attribute tags. On GenEval, LOCUS repairs 48.1% of failed generations in one rollout, compared with 37.4% for prefix optimization, and needs 14% fewer rounds on average to succeed.

arXiv (Cornell University)
Generative Adversarial Networks and Image Synthesis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon