Concept Learning with Energy-Based Models

使用能量模型进行概念学习.

Big Transfer (BiT): General Visual Representation Learning

BiT：用于迁移学习的预训练卷积神经网络模型.

Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning

分治的蒙特卡洛树搜索解决目标导向的强化学习问题.

Reinforcement Learning with Augmented Data

RAD：把数据增广方法应用到强化学习.

TAPAS: Weakly Supervised Table Parsing via Pre-training

用BERT解决表格问答任务.

Jukebox: A Generative Model for Music

使用VQ-VAE(向量量化的变分自编码器)进行音乐生成.