Yonghui Wu

5

Papers

1,630

Total Citations

Papers (5)

Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

Reward Augmented Maximum Likelihood for Neural Structured Prediction

NeurIPS 2016arXiv

VILA: Learning Image Aesthetics From User Comments With Vision-Language Pretraining

Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis

GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism