AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

ToProVAR: Efficient Visual Autoregressive Modeling via Tri-Dimensional Entropy-Aware Semantic Analysis and Sparsity Optimization

Jiayu Chen, Ruoyu Lin, Zihao Zheng, Jingxin Le, Maoliang Li, Guojie Luo, Xiang Chen

ICLR 2026 · Image generation › Autoregressive and latent generation · approach: Next-scale and token autoregressive images · 5 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
apply ToProVAR token/layer/scale pruningInfinity-2B · GenEval overallscore: 0.69 -> 0.69No clear effect
apply ToProVARInfinity-2B · latencyseconds: 2.10 -> 0.61Improved
apply ToProVARInfinity-8B · latencyseconds: 4.86 -> 1.78Improved
use ToProVAR instead of FastVAR on MJHQ30K PeopleInfinity-2B · FIDFID: 71.8 -> 58.84Improved
add Layer Representation Identification to scale-only pruning (ablation)ToProVAR Infinity-2B · GenEvalscore: 0.477 -> 0.679Improved
add fine-grained token pruning (restricted to detail layers) (ablation)ToProVAR Infinity-2B · GenEvalscore: 0.679 -> 0.690Improved
add token pruning on all layers without layer identification (ablation)Scale Depth Loc. · GenEvalscore: 0.477 -> 0.603Improved
use adaptive Scale Depth Localization instead of fixed scale exit (ablation)Infinity-2B · GenEvalscore: 0.403 -> 0.477Improved
use Flash Attention Entropy instead of naive entropy (ablation)ToProVAR Infinity-2B · latencyseconds: 1.10 -> 0.61Improved
apply ToProVAR to HARTHART · GenEval overallscore: 0.51 -> 0.51No clear effect
apply ToProVAR instead of FastVAR on HPSv2.1Infinity-8B · HPSv2.1 overallscore: 30.99 -> 30.58Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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