AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

ProtoVAR: Efficient Dataset Distillation via Prototype-Guided Visual Autoregressive Modeling

Mingyu Wang, Wei Jiang

ICML 2026 · Image generation › Fast diffusion sampling · approach: Distillation for few-step generation

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 prototype-guided generation (ablation)VAR · ImageWoof IPC10accuracy: 38.8 -> 43.2Improved
add prototype-guided generation (ablation)VAR · ImageWoof IPC50accuracy: 62.8 -> 69.5Improved
add prototype-guided generation (ablation)VAR · ImageNette IPC10accuracy: 58.3 -> 65.3Improved
add prototype-guided generation (ablation)VAR · ImageNette IPC50accuracy: 78.1 -> 82.1Improved
add target-guided filtering alone (ablation)VAR · ImageWoof IPC10accuracy: 38.8 -> 42.6Improved
add target-guided filtering alone (ablation)VAR · ImageNette IPC10accuracy: 58.3 -> 64.1Improved
add target-guided filtering to prototype guidance (ablation)ProtoVAR · ImageWoof IPC10accuracy: 43.2 -> 47.2Improved
add target-guided filtering to prototype guidance (ablation)ProtoVAR · ImageWoof IPC50accuracy: 69.5 -> 72.0Improved
add target-guided filtering to prototype guidance (ablation)ProtoVAR · ImageNette IPC50accuracy: 82.1 -> 85.8Improved
add 5x candidate pool with random selection (ablation)ProtoVAR (w/o pool) · ImageWoof IPC10accuracy: 43.2 -> 45.1Improved
add 5x candidate pool with random selection (ablation)ProtoVAR (w/o pool) · ImageNette IPC50accuracy: 82.1 -> 84.2Improved
replace random pool selection with teacher-guided filtering (ablation)ProtoVAR (rand) · ImageWoof IPC50accuracy: 70.6 -> 72.0Improved

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