Publications

Loic Matthey, SIMA team (2024). Scalable Instructable Multiworld Agent (SIMA) - A generalist AI agent for 3D virtual environments. Google DeepMind Blog.

PDF Blog post

Drew A. Hudson, Daniel Zoran, Mateusz Malinowski, Andrew K Lampinen, Andrew Jaegle, James L McClelland, Loic Matthey, Felix Hill, Alexander Lerchner (2023). SODA: Bottleneck Diffusion Models for Representation Learning. arXiv.

PDF

Rishabh Kabra, Loic Matthey, Alexander Lerchner, Niloy J Mitra (2023). Evaluating VLMs for Score-Based, Multi-Probe Annotation of 3D Objects. arXiv.

PDF

Rishabh Kabra, Daniel Zoran, Goker Erdogan, Loic Matthey, Antonia Creswell, Matthew Botvinick, Alexander Lerchner, Christopher P Burgess (2021). SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition. NeurIPS 2021.

PDF Cite Animated figures

Nicholas Watters, Loic Matthey, Christopher P Burgess, Alexander Lerchner (2019). Spatial Broadcast Decoder: A simple architecture for learning disentangled representations in VAEs. ICLR 2019 Workshop on Learning from Limited Labeled Data.

PDF Cite

Loic Matthey, Nicholas Watters, Matko Bosnjak, Christopher P Burgess, Alexander Lerchner (2019). COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration. arXiv.

PDF Cite Code Twitter thread explainer

Klaus Greff, Raphael Lopez Kaufmann, Rishabh Kabra, Nicholas Watters, Christopher P Burgess, Daniel Zoran, Loic Matthey, Matthew Botvinick, Alexander Lerchner (2019). Multi-Object Representation Learning with Iterative Variational Inference. ICML 2019.

PDF Cite

Christopher P Burgess, Loic Matthey, Nicholas Watters, Rishabh Kabra, Irina Higgins, Matthew Botvinick, Alexander Lerchner (2019). MONet: Unsupervised Scene Decomposition and Representation. arXiv.

PDF Cite

Christopher P Burgess, Irina Higgins, Arka Pal, Loic Matthey, Nicholas Watters, Guillaume Desjardins, Alexander Lerchner (2018). Understanding disentangling in β-VAE. 2017 NIPS Workshop on Learning Disentangled Representations.

PDF Cite

Irina Higgins, Arka Pal, Andrei Rusu, Loic Matthey, Christopher P Burgess, Alexander Pritzel, Matthew Botvinick, Charles Blundell, Alexander Lerchner (2017). DARLA: Improving zero-shot transfer in reinforcement learning. ICML 2017.

PDF Cite arXiv

Irina Higgins, Nicolas Sonnerat, Loic Matthey, Arka Pal, Christopher P Burgess, Matthew Botvinick, Demis Hassabis, Alexander Lerchner (2017). SCAN: Learning Abstract Hierarchical Compositional Visual Concepts. arXiv.

PDF Cite DeepMind Blog

Loic Matthey, Irina Higgins, Christopher P Burgess, Demis Hassabis, Alexander Lerchner (2017). dSprites: Disentanglement testing Sprites dataset. Github.

Cite Dataset

Irina Higgins, Loic Matthey, Arka Pal, Christopher P Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, Alexander Lerchner (2017). β-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. ICLR 2017.

PDF Cite Dataset Paper