mlsanityData to 14 Oct 2026

PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications

arXiv 1701.05517 ↗First posted 19 Jan 2017cs.LG stat.MLcited by 417

Not on the map. Why?

Cited by 100 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

PixelCNNs are a recently proposed class of powerful generative models with tractable likelihood. Here we discuss our implementation of PixelCNNs which we make available at https://github.com/openai/pixel-cnn. Our implementation contains a number of modifications to the original model that both simplify its structure and improve its performance. 1) We use a discretized logistic mixture likelihood on the pixels, rather than a 256-way softmax, which we find to speed up training. 2) We condition on whole pixels, rather than R/G/B sub-pixels, simplifying the model structure. 3) We use downsampling to efficiently capture structure at multiple resolutions. 4) We introduce additional short-cut connections to further speed up optimization. 5) We regularize the model using dropout. Finally, we present state-of-the-art log likelihood results on CIFAR-10 to demonstrate the usefulness of these modifications.

Key facts. Cited by 417 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Jan 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 99; 2022: 98; 2023: 68; 2024: 66; 2025: 57; 2026: 28.

417 papers.

Sort:

By area:

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2022Scalable Diffusion Models with Transformerscited by 6,054
  3. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  4. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  5. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  6. 2022Video Diffusion Modelscited by 2,305
  7. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,778
  8. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  9. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  10. 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
  11. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,163
  12. 2021Variational Diffusion Modelscited by 1,153
38 more
  1. 2022Diffusion Models in Vision: A Surveycited by 1,015
  2. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 774
  3. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 672
  4. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 658
  5. 2021Score-based Generative Modeling in Latent Spacecited by 636
  6. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 626
  7. 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 485
  8. 2022A Continuous Time Framework for Discrete Denoising Modelscited by 451
  9. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 373
  10. 2021GAN Inversion: A Surveycited by 367
  11. 2022MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolationcited by 309
  12. 2022Perception Prioritized Training of Diffusion Modelscited by 303
  13. 2021Generating Images with Sparse Representationscited by 266
  14. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  15. 2023MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizercited by 262
  16. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 252
  17. 2021Autoregressive Diffusion Modelscited by 210
  18. 2021ATISS: Autoregressive Transformers for Indoor Scene Synthesiscited by 200
  19. 2022Can large language models reason about medical questions?cited by 194
  20. 2022It's Raw! Audio Generation with State-Space Modelscited by 171
  21. 2023MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformerscited by 170
  22. 2022Generative Modelling With Inverse Heat Dissipationcited by 167
  23. 2022Concrete Score Matching: Generalized Score Matching for Discrete Datacited by 148
  24. 2022What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Datacited by 138
  25. 2021High-Fidelity Pluralistic Image Completion with Transformerscited by 134
  26. 2021ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesiscited by 122
  27. 2024Scalable Pre-training of Large Autoregressive Image Modelscited by 115
  28. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 109
  29. 2021Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAEcited by 106
  30. 2021Geometry-Free View Synthesis: Transformers and no 3D Priorscited by 100
  31. 2023PreDiff: Precipitation Nowcasting with Latent Diffusion Modelscited by 98
  32. 20223DILG: Irregular Latent Grids for 3D Generative Modelingcited by 93
  33. 2021Understanding Failures in Out-of-Distribution Detection with Deep Generative Modelscited by 89
  34. 2023Reflected Diffusion Modelscited by 87
  35. 2023Self-Supervised Video Forensics by Audio-Visual Anomaly Detectioncited by 85
  36. 2025Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunitiescited by 85
  37. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  38. 2022Latent Plans for Task-Agnostic Offline Reinforcement Learningcited by 81

50 most cited of 417 All 417 (JSON)