Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

SayCan: 结合语言模型与机器人的功能可见性.

On Self Modulation for Generative Adversarial Networks

生成对抗网络的自调制.

Large Scale GAN Training for High Fidelity Natural Image Synthesis

BigGAN：用于高保真度自然图像合成的大规模GAN.

Taming Transformers for High-Resolution Image Synthesis

通过VQGAN和Transformer实现高分辨率图像合成.

Self-Attention Generative Adversarial Networks

SAGAN：自注意力生成对抗网络.

cGANs with Projection Discriminator

通过投影判别器构造条件生成对抗网络.