Search Results for author: Teven Le Scao

Found 6 papers, 4 papers with code

How Many Data Points is a Prompt Worth?

1 code implementation NAACL 2021 Teven Le Scao, Alexander M. Rush

When fine-tuning pretrained models for classification, researchers either use a generic model head or a task-specific prompt for prediction.

Classification General Classification

Neural Differential Equations for Single Image Super-resolution

no code implementations2 May 2020 Teven Le Scao

Although Neural Differential Equations have shown promise on toy problems such as MNIST, they have yet to be successfully applied to more challenging tasks.

Image Restoration Image Super-Resolution

In-training Matrix Factorization for Parameter-frugal Neural Machine Translation

no code implementations27 Sep 2019 Zachary Kaden, Teven Le Scao, Raphael Olivier

In this paper, we propose the use of in-training matrix factorization to reduce the model size for neural machine translation.

Machine Translation

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