Pith. sign in

REVIEW 11 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1701.05517 v1 pith:4L6ZCE7B submitted 2017-01-19 cs.LG stat.ML

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

Tim Salimans , Andrej Karpathy , Xi Chen , Diederik P. Kingma This is my paper
classification cs.LG stat.ML
keywords likelihoodmodelmodificationsstructurediscretizedimplementationlogisticmixture
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Efficiently Modeling Long Sequences with Structured State Spaces

    cs.LG 2021-10 unverdicted novelty 8.0

    S4 is an efficient state space sequence model that captures long-range dependencies via structured parameterization of the SSM, achieving state-of-the-art results on the Long Range Arena and other benchmarks while bei...

  2. Parallel Jacobi Decoding for Fast Autoregressive Image Generation

    cs.CV 2026-06 conditional novelty 7.0

    Parallel Jacobi Decoding accelerates autoregressive image models 4.8x-6.4x by using 2D spatial draft expansion and adjusted attention masks while keeping generation quality competitive.

  3. Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories

    cs.LG 2025-10 unverdicted novelty 7.0

    DISC extracts multi-statistic trajectories from diffusion denoising to both detect and classify types of distributional shifts in OOD data.

  4. Scalable Diffusion Models with Transformers

    cs.CV 2022-12 unverdicted novelty 7.0

    DiTs achieve SOTA FID of 2.27 on ImageNet 256x256 by scaling transformer-based latent diffusion models, with performance improving consistently as Gflops increase.

  5. High-Resolution Image Synthesis with Latent Diffusion Models

    cs.CV 2021-12 conditional novelty 7.0

    Latent diffusion models achieve state-of-the-art inpainting and competitive results on unconditional generation, scene synthesis, and super-resolution by performing the diffusion process in the latent space of pretrai...

  6. Generating Long Sequences with Sparse Transformers

    cs.LG 2019-04 unverdicted novelty 7.0

    Sparse Transformers factorize attention to handle sequences tens of thousands long, achieving new SOTA density modeling on Enwik8, CIFAR-10, and ImageNet-64.

  7. Benchmarking Neural Speech Compression from a Rate-Distortion Perspective

    eess.AS 2026-06 unverdicted novelty 6.0

    ECC integrates hyperprior side information, channel-wise context, latent residual prediction, temporal modeling, and entropy skip into a learned entropy model, yielding 39.9% and 76.3% average BD-rate reductions on Vi...

  8. VideoGPT: Video Generation using VQ-VAE and Transformers

    cs.CV 2021-04 accept novelty 6.0

    VideoGPT generates competitive natural videos by learning discrete latents with VQ-VAE and modeling them autoregressively with a transformer.

  9. Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks

    cs.CV 2026-06 unverdicted novelty 5.0

    Iterative self-improving codebooks enhance safety in autoregressive multimodal models by self-identifying unsafe generations and updating the codebook to eliminate harmful visual token mappings without external feedback.

  10. Shaping Belief States with Generative Environment Models for RL

    cs.LG 2019-06 unverdicted novelty 5.0

    Multi-step predictive generative models form stable belief states capturing environment layout and agent pose, yielding higher data efficiency on RL tasks than model-free agents.

  11. CSD: Content-aware Speculative Decoding for Efficient Image Generation

    cs.CV 2026-06 unverdicted novelty 4.0

    CSD adds content-aware entropy relaxation and a distribution alignment filter to speculative decoding, raising acceptance rates in low-detail image areas while keeping output aligned with the target model.