AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models

Mingue Park, Prin Phunyaphibarn, Phillip (Yuseung) Lee, Minhyuk Sung

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Inference-time T2I improvement · 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
add condition annealing (text-embedding noise) (ablation)Infinity · MJHQ-30KLPIPS-MPD: 0.33 -> 0.56Improved
add condition annealing (text-embedding noise) (ablation)Infinity · MJHQ-30KImageReward: 1.22 -> 0.49Hurt
add scale-travel refinement after condition annealing (ablation)Infinity · MJHQ-30KImageReward: 0.49 -> 1.08Improved
add scale-travel refinement after condition annealing (ablation)Infinity · MJHQ-30KLPIPS-MPD: 0.56 -> 0.48Hurt
add scale-travel refinement after condition annealing (ablation)Infinity · MS-COCOFID: 22.51 -> 28.97Hurt
add condition annealing (text-embedding noise) (ablation)Switti · MJHQ-30KFID: 16.18 -> 21.34Hurt
add scale-travel refinement after condition annealing (ablation)Switti · MJHQ-30KFID: 21.34 -> 17.30Improved
add condition annealing (text-embedding noise) (ablation)InfinityStar · VBenchdiversity: 0.270 -> 0.627Improved
add scale-travel refinement after condition annealing (ablation)InfinityStar · VBenchquality score: 0.794 -> 0.804Improved
add scale-travel refinement after condition annealing (ablation)InfinityStar · VBenchdiversity: 0.627 -> 0.487Hurt
raise sampling temperature from 1 to 10 (ablation)Infinity · MJHQ-30KImageReward: 1.323 -> -0.430Hurt
raise nucleus sampling p from 0.9 to 1.0 (ablation)Infinity · MJHQ-30KLPIPS-MPD: 0.323 -> 0.335No clear effect

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