collaborators

6 papers

cs.IT2024

Computing Low-Entropy Couplings for Large-Support Distributions

Samuel Sokota, Dylan Sam, Christian Schroeder de Witt +3

Minimum-entropy coupling (MEC) -- the process of finding a joint distribution with minimum entropy for given marginals -- has applications in areas such as causality and steganogra…

cs.LG2024

Risks and Opportunities of Open-Source Generative AI

Francisco Eiras, Aleksandar Petrov, Bertie Vidgen +22

Applications of Generative AI (Gen AI) are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for these seismic chan…

cs.LG2024

Near to Mid-term Risks and Opportunities of Open-Source Generative AI

Francisco Eiras, Aleksandar Petrov, Bertie Vidgen +21

In the next few years, applications of Generative AI are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for thes…

cs.LG2024

Select to Perfect: Imitating desired behavior from large multi-agent data

Tim Franzmeyer, Edith Elkind, Philip Torr +2

AI agents are commonly trained with large datasets of demonstrations of human behavior. However, not all behaviors are equally safe or desirable. Desired characteristics for an AI…

cs.AI2024

Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks

Tim Franzmeyer, Stephen McAleer, João F. Henriques +4

Autonomous agents deployed in the real world need to be robust against adversarial attacks on sensory inputs. Robustifying agent policies requires anticipating the strongest attack…

cs.LG2024

Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection

Linas Nasvytis, Kai Sandbrink, Jakob Foerster +2

While reinforcement learning (RL) algorithms have been successfully applied across numerous sequential decision-making problems, their generalization to unforeseen testing environm…