AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Vision Bridge Transformer at Scale

Zhenxiong Tan, Zeqing Wang, Xingyi Yang, Songhua Liu, Xinchao Wang

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 6 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 stabilized velocity matching instead of displacement matching (ablation)ViBT · Depth-to-videoVBench Score: 0.695 -> 0.71Improved
use stabilized velocity matching instead of plain velocity matching (ablation)ViBT · Depth-to-videoVBench Score: 0.698 -> 0.71Improved
use stabilized velocity matching instead of displacement matching (ablation)ViBT · ImgEdit-Benchaverage score: 3.50 -> 3.55Improved
use stabilized velocity matching instead of plain velocity matching (ablation)ViBT · ImgEdit-Benchaverage score: 3.36 -> 3.55Improved
lower noise scale to s=0.5 from s=1 (ablation)ViBT · ImgEdit-Benchaverage score: 3.55 -> 3.76Improved
lower noise scale to s=0.5 from s=1 (ablation)ViBT · Depth-to-videoVBench Score: 0.709 -> 0.666Hurt
raise noise scale to s=2 from s=1 (ablation)ViBT · Depth-to-videoVBench Score: 0.709 -> 0.711No clear effect
raise noise scale to s=2 from s=1 (ablation)ViBT · ImgEdit-Benchaverage score: 3.55 -> 3.44Hurt
raise noise scale to s=4 from s=1 (ablation)ViBT · Depth-to-videoVBench Score: 0.709 -> 0.482Hurt
remove noise (s=0) versus s=1 (ablation)ViBT · ImgEdit-Benchaverage score: 3.55 -> 3.10Hurt
use variance-corrected sampling instead of naive Euler-Maruyama (ablation)ViBT · image editingvisual qualityImproved
use shifted timestep schedule gamma=5 instead of linear (ablation)ViBT · image editingvisual qualityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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