Papers

Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention

Papers

ALBERT: A Lite BERT for Self-Supervised Learning of Language Representations

Papers

Model based Reinforcement Learning for Atari

Papers

Deep Learning without Weight Transport

Papers

Agent 57: Outperforming the Atari Human Benchmark

Papers

ViLBERT

Papers

Experience Replay for Continual Learning

Papers

Finding Friend or Foe in Multi-Agent Games

Papers

Revisiting Self-Supervised Visual Representation Learning

Papers

Learning Unsupervised Learning Rules