Search Results for author: Sai Prasanna

Found 3 papers, 2 papers with code

Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization

1 code implementation16 Mar 2024 Sai Prasanna, Karim Farid, Raghu Rajan, André Biedenkapp

Toward the goal of ZSG to unseen variation in context, we propose the contextual recurrent state-space model (cRSSM), which introduces changes to the world model of the Dreamer (v3) (Hafner et al., 2023).

Zero-shot Generalization

When BERT Plays the Lottery, All Tickets Are Winning

no code implementations EMNLP 2020 Sai Prasanna, Anna Rogers, Anna Rumshisky

Large Transformer-based models were shown to be reducible to a smaller number of self-attention heads and layers.

Cannot find the paper you are looking for? You can Submit a new open access paper.