AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Spanning Tree Autoregressive Visual Generation

Sangkyu Lee, Changho Lee, Janghoon Han, Hosung Song, Tackgeun You, Hwasup Lim, Stanley Jungkyu Choi, Honglak Lee, Youngjae Yu

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: Next-scale and token autoregressive images · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use spanning tree BFS orders in training instead of random permutation throughout (ablation)STAR-B · ImageNet-1k generationFID: 3.57 -> 2.24Improved
use spanning tree orders at inference for a permutation-trained model (ablation)STAR-B · ImageNet-1k generationFID: 3.57 -> 3.58No clear effect
anneal permutation to spanning tree orders at end of training (ablation)STAR-B · ImageNet-1k generationFID: 3.58 -> 2.31Improved
train with spanning tree from the start rather than annealing from permutation (ablation)STAR-B · ImageNet-1k generationFID: 2.31 -> 2.24Improved
use spanning tree orders instead of raster-scan for training and inference (ablation)STAR-B · ImageNet-1k inpaintingFID: 3.91 -> 2.39Improved
use spanning tree orders instead of raster-scan for training and inference (ablation)STAR-B · ImageNet-1k generationFID: 2.04 -> 2.24Hurt
use BFS instead of DFS for spanning tree traversal (ablation)STAR · rejection sampling over masks 0.1-0.9Trials at mask ratio 0.1: 60.45 -> 5.59Improved
use BFS with farthest root instead of random root (ablation)STAR · rejection sampling over masks 0.1-0.9Trials at mask ratio 0.1: 5.59 -> 4.41Improved
replace DiT inpainting by latent blending with STAR native prefix inpaintingSTAR-L · ImageNet-1k inpainting (L-size)FID: 4.58 -> 2.20Improved
use STAR instead of RandARSTAR-L · ImageNet-1k inpainting (L-size)FID: 2.66 -> 2.20Improved
use STAR instead of RAR at L-sizeSTAR-L · ImageNet-1k generation (L-size)FID: 1.70 -> 1.98Hurt
use STAR instead of RAR at inpaintingSTAR-L · ImageNet-1k inpainting (L-size)FID: 3.56 -> 2.20Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy