| Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts? A Filos, P Tigas, R McAllister, N Rhinehart, S Levine, Y Gal ICML 2020, 2020 | 208 | 2020 |
| Shifts: A dataset of real distributional shift across multiple large-scale tasks A Malinin, N Band, G Chesnokov, Y Gal, MJF Gales, A Noskov, ... arXiv preprint arXiv:2107.07455, 2021 | 129 | 2021 |
| PERCIVAL: Making In-Browser Perceptual Ad Blocking Practical with Deep Learning Z Abi Din, P Tigas, ST King, B Livshits 2020 USENIX Annual Technical Conference (USENIX ATC 20), 387-400, 2020 | 37* | 2020 |
| Interventions, Where and How? Experimental Design for Causal Models at Scale P Tigas, Y Annadani, A Jesson, B Schölkopf, Y Gal, S Bauer Neural Information Processing Systems 35 (1), 2022 | 36 | 2022 |
| Causal-bald: Deep bayesian active learning of outcomes to infer treatment-effects from observational data A Jesson, P Tigas, J van Amersfoort, A Kirsch, U Shalit, Y Gal Advances in Neural Information Processing Systems 34, 30465-30478, 2021 | 31 | 2021 |
| Exploration and preference satisfaction trade-off in reward-free learning N Sajid, P Tigas, A Zakharov, Z Fountas, K Friston arXiv preprint arXiv:2106.04316, 2021 | 23 | 2021 |
| Differentiable multi-target causal bayesian experimental design P Tigas, Y Annadani, DR Ivanova, A Jesson, Y Gal, A Foster, S Bauer International Conference on Machine Learning, 34263-34279, 2023 | 13* | 2023 |
| Deep Reinforcement Learning for Autonomous Robotic Tensegrity (ART) T Hosmer, P Tigas 39th Annual Conference of the Association for Computer Aided Design in …, 2019 | 12 | 2019 |
| Spatial Assembly: Generative Architecture With Reinforcement Learning, Self Play and Tree Search P Tigas, T Hosmer Workshop on Machine Learning for Creativity and Design at the 34rd …, 2020 | 11* | 2020 |
| Global geomagnetic perturbation forecasting using Deep Learning V Upendran, P Tigas, B Ferdousi, T Bloch, MCM Cheung, S Ganju, ... Space Weather, e2022SW003045, 2022 | 10* | 2022 |
| The Cave Of Sounds: An Interactive Installation Exploring How We Create Music Together T Murray-Browne, D Aversano, S Garcia, W Hobbes, D Lopez, T Sendon, ... NIME, 2014 | 9 | 2014 |
| Emergent interfaces: Vague, complex, bespoke and embodied interaction between humans and computers T Murray-Browne, P Tigas Applied Sciences 11 (18), 8531, 2021 | 8 | 2021 |
| Real2sim: Automatic Generation of Open Street Map Towns For Autonomous Driving Benchmarks A Mondal, P Tigas, Y Gal | 6 | 2020 |
| Active inference, preference learning and adaptive behaviour N Sajid, P Tigas, K Friston IOP Conference Series: Materials Science and Engineering 1261 (1), 012020, 2022 | 5 | 2022 |
| A Multilevel Low-Rank Newton Method with Super-linear Convergence Rate and its Application to Non-convex Problems N Tsipinakis, P Tigkas, P Parpas arXiv preprint arXiv:2305.08742, 2023 | 2 | 2023 |
| Unravelling A Regulation Machine: Fake News, Toxic Comments And'Illegitimate'Culture D Mylonaki, P Tigas A Peer-Reviewed Journal About 7 (1), 86-98, 2018 | 2 | 2018 |
| Modelling non-reinforced preferences using selective attention N Sajid, P Tigas, Z Fountas, Q Guo, A Zakharov, L Da Costa arXiv preprint arXiv:2207.13699, 2022 | 1 | 2022 |
| Deep Bayesian Active Learning for Preference Modeling in Large Language Models LC Melo, P Tigas, A Abate, Y Gal arXiv preprint arXiv:2406.10023, 2024 | | 2024 |
| Challenges and Considerations in the Evaluation of Bayesian Causal Discovery AM Karimi Mamaghan, P Tigas, KH Johansson, Y Gal, Y Annadani, ... arXiv e-prints, arXiv: 2406.03209, 2024 | | 2024 |
| Amortized Active Causal Induction with Deep Reinforcement Learning Y Annadani, P Tigas, S Bauer, A Foster arXiv preprint arXiv:2405.16718, 2024 | | 2024 |
Yarin GalAssociate Professor, University of OxfordVerified email at cs.ox.ac.uk
