1. ERNIE-ViLG: Unified generative pre-training for bidirectional vision-language generation;zhang,2021
2. The expressive power of neural networks: A view from the width;lu;Proc Adv Neural Inf Process Syst (NIPS),0
3. What makes multimodal learning better than single (Provably);huang;Proc Adv Neural Inf Process Syst (NIPS),0
4. Zero-shot text-to-image generation;ramesh,2021
5. FastMoE: A fast mixture-of-expert training system;he,2021