Research map / Image generation / Fast diffusion sampling
Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 patch-based attention over support-image features (ablation) | PixelCNN · ImageNet flipping | nats/dim: 2.65 -> 0.90 | Helped |
| add patch-based attention over support-image features (ablation) | PixelCNN · Omniglot, 1-shot | NLL (nats/dim): 0.077(0.070) -> 0.071(0.066) | Helped |
| add patch-based attention over support-image features (ablation) | PixelCNN · Omniglot, 2-shot | NLL (nats/dim): 0.077(0.068) -> 0.068(0.064) | Helped |
| add patch-based attention over support-image features (ablation) | PixelCNN · Omniglot, 4-shot | NLL (nats/dim): 0.077(0.067) -> 0.066(0.062) | Helped |
| add patch-based attention over support-image features (ablation) | PixelCNN · Omniglot, 8-shot | NLL (nats/dim): 0.076(0.065) -> 0.064(0.060) | Helped |
| use gradient-based adaptation on support examples (ablation) | PixelCNN · Omniglot, 4-shot | NLL (nats/pixel): 0.077(0.067) -> 0.068(0.065) | Helped |
| combine attention conditioning with gradient-based weight updates (ablation) | Meta PixelCNN · Omniglot, 4-shot | NLL (nats/pixel): 0.068(0.065) -> 0.069(0.065) | Hurt |
| add patch-based attention over support-image features (ablation) | PixelCNN · Stanford Online Products | nats/dim: 2.15 -> 2.14 | No clear effect |
| add patch-based attention over support-image features (ablation) | PixelCNN · ImageNet flipping, 24 × 24 | qualitative flipping success | No clear effect |
Closest papers by meaning
- Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction (NeurIPS 2024 · similarity 0.86)
- Data-efficient Large Vision Models through Sequential Autoregression (ICML 2024 · similarity 0.86)
- Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation (CVPR 2025 · similarity 0.85)
- Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots (ICML 2025 · similarity 0.85)
- Scalable Pre-training of Large Autoregressive Image Models (ICML 2024 · similarity 0.85)
- Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction (ICLR 2025 · similarity 0.84)
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.