PixelCNN++: Improving the pixelcnn with dis- cretized logistic mixture likelihood and other modifications

representative citing papers

citing papers explorer

Showing 5 of 5 citing papers.

• Efficiently Modeling Long Sequences with Structured State Spaces cs.LG · 2021-10-31 · unverdicted · none · ref 39

  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 being faster than Transformers for generation.

• Scalable Diffusion Models with Transformers cs.CV · 2022-12-19 · unverdicted · none · ref 52

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

• High-Resolution Image Synthesis with Latent Diffusion Models cs.CV · 2021-12-20 · conditional · none · ref 73

  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 pretrained autoencoders with cross-attention conditioning, while cutting computational and

• Generating Long Sequences with Sparse Transformers cs.LG · 2019-04-23 · unverdicted · none · ref 20

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

• VideoGPT: Video Generation using VQ-VAE and Transformers cs.CV · 2021-04-20 · accept · none · ref 32

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