Paper a Week
Paper a Week
Recent Papers
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
ALBERT: A Lite BERT for Self-Supervised Learning of Language Representations
Model based Reinforcement Learning for Atari
More
Deep Learning without Weight Transport
Agent 57: Outperforming the Atari Human Benchmark
ViLBERT
Experience Replay for Continual Learning
All Papers