Research map / Image generation / Fast diffusion sampling
ProtoVAR: Efficient Dataset Distillation via Prototype-Guided Visual Autoregressive Modeling
Mingyu Wang, Wei Jiang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add prototype-guided generation (ablation) | VAR · ImageWoof IPC10 | accuracy: 38.8 -> 43.2 | Improved |
| add prototype-guided generation (ablation) | VAR · ImageWoof IPC50 | accuracy: 62.8 -> 69.5 | Improved |
| add prototype-guided generation (ablation) | VAR · ImageNette IPC10 | accuracy: 58.3 -> 65.3 | Improved |
| add prototype-guided generation (ablation) | VAR · ImageNette IPC50 | accuracy: 78.1 -> 82.1 | Improved |
| add target-guided filtering alone (ablation) | VAR · ImageWoof IPC10 | accuracy: 38.8 -> 42.6 | Improved |
| add target-guided filtering alone (ablation) | VAR · ImageNette IPC10 | accuracy: 58.3 -> 64.1 | Improved |
| add target-guided filtering to prototype guidance (ablation) | ProtoVAR · ImageWoof IPC10 | accuracy: 43.2 -> 47.2 | Improved |
| add target-guided filtering to prototype guidance (ablation) | ProtoVAR · ImageWoof IPC50 | accuracy: 69.5 -> 72.0 | Improved |
| add target-guided filtering to prototype guidance (ablation) | ProtoVAR · ImageNette IPC50 | accuracy: 82.1 -> 85.8 | Improved |
| add 5x candidate pool with random selection (ablation) | ProtoVAR (w/o pool) · ImageWoof IPC10 | accuracy: 43.2 -> 45.1 | Improved |
| add 5x candidate pool with random selection (ablation) | ProtoVAR (w/o pool) · ImageNette IPC50 | accuracy: 82.1 -> 84.2 | Improved |
| replace random pool selection with teacher-guided filtering (ablation) | ProtoVAR (rand) · ImageWoof IPC50 | accuracy: 70.6 -> 72.0 | Improved |
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.
- CaO2 — CaO2: Rectifying Inconsistencies in Diffusion-Based Dataset Distillation (ICCV 2025) · better on 3 of 3 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
- FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive Models (ICML 2026 · similarity 0.90)
- TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation (NeurIPS 2025 · similarity 0.89)
- Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction (NeurIPS 2024 · similarity 0.89)
- Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation (NeurIPS 2025 · similarity 0.88)
- FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction (NeurIPS 2025 · similarity 0.88)
- Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective (NeurIPS 2024 · similarity 0.87)
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.
