Joel Veness
Joel Veness 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, Gregoire Deletang.
OpenAlex · h-index 17 · 59 works · 39,865 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 151 citations in our library · 1 more in our library without a page yet · ⭐ Paper Star rank #3962
Affiliations
🏢Google DeepMindLondon ·
United Kingdom2012–2024 · 15 papers🎓University of AlbertaEdmonton ·
Canada2011–2021 · 13 papers🏢GoogleMountain View ·
United States2016–2020 · 4 papers🔬Data61Sydney ·
Australia2007–2010 · 4 papers🎓UNSW SydneySydney ·
Australia2007–2010 · 4 papers🔬Dalle Molle Institute for Artificial Intelligence ResearchLugano ·
Switzerland2023 · 2 papers🎓University of Applied Sciences and Arts of Southern SwitzerlandManno ·
Switzerland2023 · 2 papers🎓Australian National UniversityCanberra ·
Australia2011–2015 · 2 papers
Topics
Language models & pretraining (1) Efficient models & compression (1)
Works by year
2020s
Papers
- 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.
Also in our library
Co-authors here
- Anian Ruoss ×2
- Elliot Catt ×2
- Gregoire Deletang ×2
- Jordi Grau-Moya ×2
- Li Kevin Wenliang ×2
- Marcus Hutter ×2
- Tim Genewein ×2
- Paul-Ambroise Duquenne
Cited by
This page in Markdown → https://md.research.elamur.ai/free/en/authors/joel-veness/