Publications

Date: 21 Mar 24 21 March 2024
Title: Evaluating Frontier Models for Dangerous Capabilities
Authors: Mary Phuong, Matthew Aitchison, Elliot Catt, Scogan ‎(Sarah Cogan), Heidi Howard, Alex Kaskasoli, Victoria Krakovna, David Lindner, Matthew Rahtz, Yannis Assael, Maria Abi Raad, Tom Lieberum, Sebastian Farquhar, gdelt , Anian Ruoss, Marcus Hutter, Rohin Shah, Allan Dafoe, Toby Shevlane, Sarah Hodkinson, Sharon Lin, Albert Webson, Lewis Ho, Seliem El-Sayed, Sasha Brown
Venue: arXiv

Date: 19 Mar 24 19 March 2024
Title: DiPaCo: Distributed Path Composition
Authors: Arthur Douillard, Qixuan Feng, Andrei A. Rusu, Adhiguna Kuncoro , Yani Donchev , Rachita Chhaparia , Ionel Gog , Marc’Aurelio Ranzato, Jiajun Shen, Arthur Szlam
Venue: arXiv

Date: 11 Mar 24 11 March 2024
Title: Understanding Learning from Human Preferences
Authors: Mohammad Gheshlaghi Azar, Mark Rowland, Bilal Piot, Zhaohan Daniel Guo, Daniele Calandriello, Michal Valko, Rémi Munos
Venue: (deprecated) AISTATS2024

Date: 11 Mar 24 11 March 2024
Title: Model-free Posterior Sampling via Learning Rate Randomization
Authors: Daniil Tiapkin*, Denis Belomestny*, Daniele Calandriello, Éric Moulines*, Rémi Munos, Alexey Naumov*, Pierre Perrault*, Michal Valko, Pierre Ménard*
Venue: NeurIPS 2023

Date: 11 Mar 24 11 March 2024
Title: Demonstration-Regularized RL
Authors: Daniil Tiapkin*, Denis Belomestny*, Daniele Calandriello, Éric Moulines*, Alexey Naumov*, Pierre Perrault*, Michal Valko, Pierre Ménard*
Venue: ICLR 2024

Date: 11 Mar 24 11 March 2024
Title: Prosody for Intuitive Robotic Interface Design: It's Not What You Said, It's How You Said It
Authors: Ellie Sanoubari, Atil Iscen, Leila Takayama, Stefano Saliceti, Corbin Cunningham, Ken Caluwaerts
Venue: HRI 2024 Workshop

Date: 11 Mar 24 11 March 2024
Title: Robust Exploration via Clustering-based Density Estimation
Authors: Alaa Saade, Steven Kapturowski, Daniele Calandriello, Charles Blundell, Pablo Sprechmann, Leopoldo Sarra*, Oliver Groth, Bilal Piot, Michal Valko
Venue: ICLR 2024

Date: 4 Mar 24 4 March 2024
Title: AtP*: Efficient and scalable methods for localizing LLM behaviour to components
Authors: János Kramár, Tom Lieberum, Neel Nanda, Rohin Shah
Venue: arXiv

Date: 1 Mar 24 1 March 2024
Title: Towards Practical Reinforcement Learning for Tokamak Magnetic Control
Authors: Brendan Tracey, Andrea Michi, Yuri Chervonyi, Ian Davies, Cosmin Paduraru, Nevena Lazic, Federico Felici*, Timo Ewalds, Craig Donner, Cristian Galperti*, Jonas Buchli, Michael Neunert, Andrea Huber, Jonathan Evens, Paula Kurylowicz, Daniel J. Mankowitz, Martin Riedmiller
Venue: Fusion Engineering and Design

Date: 1 Mar 24 1 March 2024
Title: Approximating the Core of Cooperative Games
Authors: Ian Gemp, Marc Lanctot, Luke Marris, Yiran Mao, Edgar Duéñez-Guzmán, Sarah Perrin, Andras Gyorgy, Romuald Elie, Georgios Piliouras, Michael Kaisers, Daniel Hennes, Kalesha Bullard, Kate Larson, Yoram Bachrach
Venue: AAMAS 2024

Date: 29 Feb 24 29 February 2024
Title: Bad Students Make Great Teachers: Active Learning Accelerates Large Scale Visual Understanding
Authors: Talfan Evans, Shreya Pathak, Ryutaro Tanno, Hamza Merzic, Olivier Henaff
Venue: arXiv

Date: 29 Feb 24 29 February 2024
Title: Self-supervised video pretraining yields strong image representations
Authors: Nikhil Parthasarathy, Ali Eslami, Joao Carreira, Olivier Henaff
Venue: NeurIPS 2023

Date: 27 Feb 24 27 February 2024
Title: Set Learning for Accurate and Calibrated Models
Authors: Lukas Muttenthaler, Robert Vandermeulen, Richard Zhang, Thomas Unterthiner, Klaus-Robert Mueller
Venue: ICLR 2024

Date: 26 Feb 24 26 February 2024
Title: A density estimation perspective on learning from pairwise human preferences
Authors: Vincent Dumoulin, Daniel Johnson, Pablo Castro Rivadeneira, Hugo Larochelle, Yann Dauphin
Venue: Transactions on Machine Learning Research (TMLR)

Date: 25 Feb 24 25 February 2024
Title: Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers
Authors: Krzysztof Marcin Choromanski, Shanda Li, Valerii Likhosherstov, Kumar Avinava Dubey, Shengjie Luo, Di He, Yiming Yang, Tamas Sarlos, Thomas Weingarten, Adrian Weller
Venue: (deprecated) AISTATS2024

Date: 23 Feb 24 23 February 2024
Title: AlphaTensor for Optimizing Quantum Computations
Authors: Francisco Ruiz, Tuomas Laakkonen*, Johannes Bausch, Matej Balog, Mohammadamin Barekatain*, Francisco Heras, Alexander Novikov, Nathan Fitzpatrick*, Bernardino Romera Paredes, John van de Wetering*, Alhussein Fawzi, Konstantinos Meichanetzidis*, Pushmeet Kohli
Venue: arXiv