Grégoire Delétang

Grégoire Delétang has 2 papers in our library, in 2022–2023, most of them on Language models & pretraining, Efficient models & compression; often with Anian Ruoss, Elliot Catt, Joel Veness.

2 papers in our library · 2022–2023

The profile is the library's match of the name; two people with one name are not always told apart.

Topics

The most cited first (OpenAlex and our library).

Language Modeling Is Compression (2023 · 89 citations)
The paper revisits the old equivalence between prediction and lossless compression and uses it to evaluate large pretrained models.
Neural Networks and the Chomsky Hierarchy (2022 · 66 citations)
The authors investigate whether the theory of computation, specifically the Chomsky hierarchy, can predict where the ability of neural networks to generalize out of distribution ends.

1 more work of theirs is in our library without a page here yet; it will appear as we publish them.

8 co-authors with a page, the most papers together first.

Papers of our library cite their works 147 times (of the 140 884 papers whose bibliographies we read); 15 citing papers with a page here →.