Alert button
Picture for Charles Blundell

Charles Blundell

Alert button

Synth$^2$: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings

Mar 12, 2024
Sahand Sharifzadeh, Christos Kaplanis, Shreya Pathak, Dharshan Kumaran, Anastasija Ilic, Jovana Mitrovic, Charles Blundell, Andrea Banino

Viaarxiv icon

Improving fine-grained understanding in image-text pre-training

Jan 18, 2024
Ioana Bica, Anastasija Ilić, Matthias Bauer, Goker Erdogan, Matko Bošnjak, Christos Kaplanis, Alexey A. Gritsenko, Matthias Minderer, Charles Blundell, Razvan Pascanu, Jovana Mitrović

Viaarxiv icon

Unlocking the Power of Representations in Long-term Novelty-based Exploration

May 02, 2023
Alaa Saade, Steven Kapturowski, Daniele Calandriello, Charles Blundell, Pablo Sprechmann, Leopoldo Sarra, Oliver Groth, Michal Valko, Bilal Piot

Figure 1 for Unlocking the Power of Representations in Long-term Novelty-based Exploration
Figure 2 for Unlocking the Power of Representations in Long-term Novelty-based Exploration
Figure 3 for Unlocking the Power of Representations in Long-term Novelty-based Exploration
Figure 4 for Unlocking the Power of Representations in Long-term Novelty-based Exploration
Viaarxiv icon

Neural Algorithmic Reasoning with Causal Regularisation

Feb 20, 2023
Beatrice Bevilacqua, Kyriacos Nikiforou, Borja Ibarz, Ioana Bica, Michela Paganini, Charles Blundell, Jovana Mitrovic, Petar Veličković

Figure 1 for Neural Algorithmic Reasoning with Causal Regularisation
Figure 2 for Neural Algorithmic Reasoning with Causal Regularisation
Figure 3 for Neural Algorithmic Reasoning with Causal Regularisation
Figure 4 for Neural Algorithmic Reasoning with Causal Regularisation
Viaarxiv icon

SemPPL: Predicting pseudo-labels for better contrastive representations

Jan 12, 2023
Matko Bošnjak, Pierre H. Richemond, Nenad Tomasev, Florian Strub, Jacob C. Walker, Felix Hill, Lars Holger Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic

Figure 1 for SemPPL: Predicting pseudo-labels for better contrastive representations
Figure 2 for SemPPL: Predicting pseudo-labels for better contrastive representations
Figure 3 for SemPPL: Predicting pseudo-labels for better contrastive representations
Figure 4 for SemPPL: Predicting pseudo-labels for better contrastive representations
Viaarxiv icon

A Generalist Neural Algorithmic Learner

Sep 22, 2022
Borja Ibarz, Vitaly Kurin, George Papamakarios, Kyriacos Nikiforou, Mehdi Bennani, Róbert Csordás, Andrew Dudzik, Matko Bošnjak, Alex Vitvitskyi, Yulia Rubanova, Andreea Deac, Beatrice Bevilacqua, Yaroslav Ganin, Charles Blundell, Petar Veličković

Figure 1 for A Generalist Neural Algorithmic Learner
Figure 2 for A Generalist Neural Algorithmic Learner
Figure 3 for A Generalist Neural Algorithmic Learner
Figure 4 for A Generalist Neural Algorithmic Learner
Viaarxiv icon

Human-level Atari 200x faster

Sep 15, 2022
Steven Kapturowski, Víctor Campos, Ray Jiang, Nemanja Rakićević, Hado van Hasselt, Charles Blundell, Adrià Puigdomènech Badia

Figure 1 for Human-level Atari 200x faster
Figure 2 for Human-level Atari 200x faster
Figure 3 for Human-level Atari 200x faster
Figure 4 for Human-level Atari 200x faster
Viaarxiv icon

The CLRS Algorithmic Reasoning Benchmark

Jun 04, 2022
Petar Veličković, Adrià Puigdomènech Badia, David Budden, Razvan Pascanu, Andrea Banino, Misha Dashevskiy, Raia Hadsell, Charles Blundell

Figure 1 for The CLRS Algorithmic Reasoning Benchmark
Figure 2 for The CLRS Algorithmic Reasoning Benchmark
Figure 3 for The CLRS Algorithmic Reasoning Benchmark
Figure 4 for The CLRS Algorithmic Reasoning Benchmark
Viaarxiv icon

Retrieval-Augmented Reinforcement Learning

Mar 09, 2022
Anirudh Goyal, Abram L. Friesen, Andrea Banino, Theophane Weber, Nan Rosemary Ke, Adria Puigdomenech Badia, Arthur Guez, Mehdi Mirza, Peter C. Humphreys, Ksenia Konyushkova, Michal Valko, Simon Osindero, Timothy Lillicrap, Nicolas Heess, Charles Blundell

Figure 1 for Retrieval-Augmented Reinforcement Learning
Figure 2 for Retrieval-Augmented Reinforcement Learning
Figure 3 for Retrieval-Augmented Reinforcement Learning
Figure 4 for Retrieval-Augmented Reinforcement Learning
Viaarxiv icon