activity
20172022
most citedLanguage Models are Few-Shot Learners

3k citations · 8.5k across the 7 of their papers we have counts for

collaborators

10 papers

cs.CV20222.3k cited

Hierarchical Text-Conditional Image Generation with CLIP Latents

Aditya Ramesh, Prafulla Dhariwal, Alex Nichol +2

Contrastive models like CLIP have been shown to learn robust representations of images that capture both semantics and style. To leverage these representations for image generation…

cs.LG20212.2k cited

Diffusion Models Beat GANs on Image Synthesis

Prafulla Dhariwal, Alex Nichol

We show that diffusion models can achieve image sample quality superior to the current state-of-the-art generative models. We achieve this on unconditional image synthesis by findi…

cs.LG2021412 cited

Improved Denoising Diffusion Probabilistic Models

Alex Nichol, Prafulla Dhariwal

Denoising diffusion probabilistic models (DDPM) are a class of generative models which have recently been shown to produce excellent samples. We show that with a few simple modific…

cs.LG2020150 cited

Scaling Laws for Autoregressive Generative Modeling

Tom Henighan, Jared Kaplan, Mor Katz +16

We identify empirical scaling laws for the cross-entropy loss in four domains: generative image modeling, video modeling, multimodal imagetext models, and mathemat…

cs.CL20203k cited

Language Models are Few-Shot Learners

Tom B. Brown, Benjamin Mann, Nick Ryder +28

Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task. While typicall…

eess.AS2020107 cited

Jukebox: A Generative Model for Music

Prafulla Dhariwal, Heewoo Jun, Christine Payne +3

We introduce Jukebox, a model that generates music with singing in the raw audio domain. We tackle the long context of raw audio using a multi-scale VQ-VAE to compress it to discre…