activity
20182022
most citedPhotorealistic Text-to-Image Diffusion Models with Deep Language Understanding

2.1k citations · 2.1k across the 1 of their papers we have counts for

collaborators

6 papers

cs.CV20222.1k cited

Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding

Chitwan Saharia, William Chan, Saurabh Saxena +11

We present Imagen, a text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding. Imagen builds on the power of large tran…

eess.IV2021

Image Super-Resolution via Iterative Refinement

Chitwan Saharia, Jonathan Ho, William Chan +3

We present SR3, an approach to image Super-Resolution via Repeated Refinement. SR3 adapts denoising diffusion probabilistic models to conditional image generation and performs supe…

cs.CL2020

Non-Autoregressive Machine Translation with Latent Alignments

Chitwan Saharia, William Chan, Saurabh Saxena +1

This paper presents two strong methods, CTC and Imputer, for non-autoregressive machine translation that model latent alignments with dynamic programming. We revisit CTC for machin…

cs.LG2020

Combating False Negatives in Adversarial Imitation Learning

Konrad Zolna, Chitwan Saharia, Leonard Boussioux +4

In adversarial imitation learning, a discriminator is trained to differentiate agent episodes from expert demonstrations representing the desired behavior. However, as the trained…

eess.AS2020

Imputer: Sequence Modelling via Imputation and Dynamic Programming

William Chan, Chitwan Saharia, Geoffrey Hinton +2

This paper presents the Imputer, a neural sequence model that generates output sequences iteratively via imputations. The Imputer is an iterative generative model, requiring only a…

cs.AI2018

BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning

Maxime Chevalier-Boisvert, Dzmitry Bahdanau, Salem Lahlou +4

Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific reasons, but given the poor data efficie…