Research map / Probabilistic and scientific modeling / Variational and generative sampling
PixelSNAIL: An Improved Autoregressive Generative Model
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 |
|---|---|---|---|
| Combine causal convolutions with self-attention | PixelSNAIL · CIFAR-10 | negative log-likelihood (bits per dim): 2.90 -> 2.85 | Helped |
| Combine causal convolutions with self-attention | PixelSNAIL · ImageNet 32 × 32 | negative log-likelihood (bits per dim): 3.81 -> 3.80 | Helped |
| Combine causal convolutions with self-attention | PixelSNAIL · ImageNet 64 × 64 | negative log-likelihood (bits per dim): 3.57 -> 3.52 | Helped |
| Use self-attention alongside causal convolutions instead of causal convolutions alone | PixelSNAIL · CIFAR-10 | negative log-likelihood (bits per dim): 3.03 -> 2.85 | Helped |
Closest papers by meaning
- Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions (ICLR 2018 · similarity 0.89)
- Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective (NeurIPS 2024 · similarity 0.87)
- Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation (NeurIPS 2025 · similarity 0.87)
- Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots (ICML 2025 · similarity 0.86)
- Data-efficient Large Vision Models through Sequential Autoregression (ICML 2024 · similarity 0.86)
- Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series (NeurIPS 2024 · similarity 0.86)
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.