GRChombo: numerical relativity with adaptive mesh refinement K Clough, P Figueras, H Finkel, M Kunesch, EA Lim, S Tunyasuvunakool Classical and Quantum Gravity 32 (24), 245011, 2015 | 132 | 2015 |

End point of black ring instabilities and the weak cosmic censorship conjecture P Figueras, M Kunesch, S Tunyasuvunakool Physical review letters 116 (7), 071102, 2016 | 116 | 2016 |

End point of the ultraspinning instability and violation of cosmic censorship P Figueras, M Kunesch, L Lehner, S Tunyasuvunakool Physical Review Letters 118 (15), 151103, 2017 | 79 | 2017 |

The DeepMind JAX Ecosystem, 2020 I Babuschkin, K Baumli, A Bell, S Bhupatiraju, J Bruce, P Buchlovsky, ... URL http://github. com/deepmind, 2010 | 71 | 2010 |

GRChombo: An adaptable numerical relativity code for fundamental physics T Andrade, LA Salo, JC Aurrekoetxea, J Bamber, K Clough, R Croft, ... arXiv preprint arXiv:2201.03458, 2022 | 45 | 2022 |

Shaking the foundations: delusions in sequence models for interaction and control PA Ortega, M Kunesch, G Delétang, T Genewein, J Grau-Moya, J Veness, ... arXiv preprint arXiv:2110.10819, 2021 | 32 | 2021 |

End point of nonaxisymmetric black hole instabilities in higher dimensions H Bantilan, P Figueras, M Kunesch, RP Macedo Physical Review D 100 (8), 086014, 2019 | 25 | 2019 |

Nonspherically symmetric collapse in asymptotically AdS spacetimes H Bantilan, P Figueras, M Kunesch, P Romatschke Physical review letters 119 (19), 191103, 2017 | 22 | 2017 |

Dimensional reduction in numerical relativity: Modified cartoon formalism and regularization WG Cook, P Figueras, M Kunesch, U Sperhake, S Tunyasuvunakool International Journal of Modern Physics D 25 (09), 1641013, 2016 | 15 | 2016 |

Human-interpretable model explainability on high-dimensional data D de Mijolla, C Frye, M Kunesch, J Mansir, I Feige arXiv preprint arXiv:2010.07384, 2020 | 12 | 2020 |

Causal analysis of agent behavior for ai safety G Déletang, J Grau-Moya, M Martic, T Genewein, T McGrath, V Mikulik, ... arXiv preprint arXiv:2103.03938, 2021 | 10 | 2021 |

Model-free risk-sensitive reinforcement learning G Delétang, J Grau-Moya, M Kunesch, T Genewein, R Brekelmans, ... arXiv preprint arXiv:2111.02907, 2021 | 9 | 2021 |

Your policy regularizer is secretly an adversary R Brekelmans, T Genewein, J Grau-Moya, G Delétang, M Kunesch, ... arXiv preprint arXiv:2203.12592, 2022 | 5 | 2022 |

Numerical simulations of instabilities in general relativity M Kunesch University of Cambridge, 2018 | 4 | 2018 |

Representation in AI Evaluations AS Bergman, LA Hendricks, M Rauh, B Wu, W Agnew, M Kunesch, I Duan, ... Proceedings of the 2023 ACM Conference on Fairness, Accountability, and …, 2023 | 2 | 2023 |

The puzzle of evaluating moral cognition in artificial agents MG Reinecke, Y Mao, M Kunesch, EA Duéñez‐Guzmán, J Haas, JZ Leibo Cognitive Science 47 (8), e13315, 2023 | 1 | 2023 |

Doing the right thing for the right reason: Evaluating artificial moral cognition by probing cost insensitivity Y Mao, MG Reinecke, M Kunesch, EA Duéñez-Guzmán, R Comanescu, ... arXiv preprint arXiv:2305.18269, 2023 | 1 | 2023 |

GRChombo: Numerical relativity simulator T Andrade, L Salo, J Aurrekoetxea, J Bamber, K Clough, R Croft, ... Astrophysics Source Code Library, ascl: 2306.039, 2023 | | 2023 |

Beyond Bayes-optimality: meta-learning what you know you don't know J Grau-Moya, G Delétang, M Kunesch, T Genewein, E Catt, K Li, A Ruoss, ... arXiv preprint arXiv:2209.15618, 2022 | | 2022 |

Stochastic Approximation of Gaussian Free Energy for Risk-Sensitive Reinforcement Learning G Delétang, J Grau-Moya, M Kunesch, T Genewein, R Brekelmans, ... | | 2021 |