Loic Matthey

Staff Research Scientist, DeepMind

Joined

November 2016

Names

Loic Matthey (Preferred)

Emails

****@google.com (Confirmed)

****@deepmind.com (Confirmed)

****@matthey.me (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Staff Research Scientist

DeepMind (google.com)

2014 – Present

Advisors, Relations & Conflicts

PhD Advisor

Peter Dayan

2009 – 2014

Expertise

Deep RL

Model-based RL

exploration

2014 – Present

generative models

VAE

2014 – Present

Publications

Leveraging VLM-Based Pipelines to Annotate 3D Objects
Rishabh Kabra, Loic Matthey, Alexander Lerchner, Niloy Mitra
- ICML 2024 Poster
- Readers: Everyone
Evaluating VLMs for Score-Based, Multi-Probe Annotation of 3D Objects
Rishabh Kabra, Loic Matthey, Alexander Lerchner, Niloy Mitra
- SyntheticData4ML 2023 Poster
- Readers: Everyone
Combining Behaviors with the Successor Features Keyboard
Wilka Carvalho, Andre Saraiva, Angelos Filos, Andrew Kyle Lampinen, Loic Matthey, Richard Lewis, Honglak Lee, Satinder Singh, Danilo Jimenez Rezende, Daniel Zoran
- NeurIPS 2023 poster
- Readers: Everyone
Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents
Jane X Wang, Michael King, Nicolas Pierre Mickael Porcel, Zeb Kurth-Nelson, Tina Zhu, Charlie Deck, Peter Choy, Mary Cassin, Malcolm Reynolds, H. Francis Song, Gavin Buttimore, David P Reichert, Neil Charles Rabinowitz, Loic Matthey, Demis Hassabis, Alexander Lerchner, Matthew Botvinick
- Published: 11 Oct 2021, Last Modified: 23 May 2023
- NeurIPS 2021 Datasets and Benchmarks Track (Round 2)
- Readers: Everyone
SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition
Rishabh Kabra, Daniel Zoran, Goker Erdogan, Loic Matthey, Antonia Creswell, Matthew Botvinick, Alexander Lerchner, Christopher P. Burgess
- Published: 09 Nov 2021, Last Modified: 26 May 2025
- NeurIPS 2021 Poster
- Readers: Everyone
SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition
Rishabh Kabra, Daniel Zoran, Goker Erdogan, Loic Matthey, Antonia Creswell, Matthew Botvinick, Alexander Lerchner, Christopher P. Burgess
- 2021 (modified: 24 Feb 2022)
- CoRR 2021
- Readers: Everyone
Alchemy: A structured task distribution for meta-reinforcement learning
Jane X. Wang, Michael King, Nicolas Porcel, Zeb Kurth-Nelson, Tina Zhu, Charlie Deck, Peter Choy, Mary Cassin, Malcolm Reynolds, H. Francis Song, Gavin Buttimore, David P. Reichert, Neil C. Rabinowitz, Loic Matthey, Demis Hassabis, Alexander Lerchner, Matthew Botvinick
- 2021 (modified: 24 Feb 2022)
- CoRR 2021
- Readers: Everyone
Constellation: Learning relational abstractions over objects for compositional imagination
James C. R. Whittington, Rishabh Kabra, Loic Matthey, Christopher P. Burgess, Alexander Lerchner
- 2021 (modified: 24 Feb 2022)
- CoRR 2021
- Readers: Everyone
Unsupervised Model Selection for Variational Disentangled Representation Learning
Sunny Duan, Loic Matthey, Andre Saraiva, Nick Watters, Christopher Burgess, Alexander Lerchner, Irina Higgins
- 2020 (modified: 24 Feb 2022)
- ICLR 2020
- Readers: Everyone
AlignNet: Unsupervised Entity Alignment
Antonia Creswell, Kyriacos Nikiforou, Oriol Vinyals, Andre Saraiva, Rishabh Kabra, Loic Matthey, Christopher Burgess, Malcolm Reynolds, Richard Tanburn, Marta Garnelo, Murray Shanahan
- 2020 (modified: 24 Feb 2022)
- CoRR 2020
- Readers: Everyone

View all 22 publications

Co-Authors

View all 61 co-authors