"Transformers are Sample Efficient World Models"

[dmm]

Another important paper from one of François Fleuret's collaborations: arxiv.org/abs/2209.00588

Previous important papers include "Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention",arxiv.org/abs/2006.16236 and "Flatten the Curve: Efficiently Training Low-Curvature Neural Networks", arxiv.org/abs/2206.07144

Comments

[dmm]

https://arxiv.org/search/cs?searchtype=author&query=Fleuret%2C+F

https://scholar.google.com/citations?user=Bj1tRlsAAAAJ&hl=en