| RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness F Pinto, H Yang, SN Lim, PHS Torr, PK Dokania NeurIPS 2022, 2022 | 96* | 2022 |
| An Impartial Take to the CNN vs Transformer Robustness Contest F Pinto, PHS Torr, PK Dokania ECCV 2022, 2022 | 64* | 2022 |
| Sample-dependent Adaptive Temperature Scaling for Improved Calibration T Joy, F Pinto, SN Lim, PHS Torr, PK Dokania AAAI 2023, 2022 | 32 | 2022 |
| Not Just Pretty Pictures: Text-to-Image Generators Enable Interpretable Interventions for Robust Representations J Yuan, F Pinto, A Davies, P Torr ICML 2024, 2022 | 26* | 2022 |
| Towards automated satellite conjunction management with Bayesian deep learning F Pinto, G Acciarini, S Metz, S Boufelja, S Kaczmarek, K Merz, ... AI4EarthScience Workshop at NeurIPS 2020, 2020 | 22 | 2020 |
| Spacecraft collision risk assessment with probabilistic programming G Acciarini, F Pinto, S Metz, S Boufelja, S Kaczmarek, K Merz, ... ML4PhysicalSciences Workshop at NeurIPS 2020, 2020 | 18 | 2020 |
| Kessler: A machine learning library for spacecraft collision avoidance G Acciarini, F Pinto, F Letizia, JA Martinez-Heras, K Merz, CP BRIDGES, ... European Conference on Space Debris, 2021 | 17 | 2021 |
| PILLAR: How to make semi-private learning more effective F Pinto, Y Hu, F Yang, A Sanyal SatML 2024, 2023 | 14 | 2023 |
| SECI-GAN: Semantic and Edge Completion for dynamic objects removal F Pinto, A Romanoni, M Matteucci, PHS Torr 2020 25th International Conference on Pattern Recognition (ICPR), 10441-10448, 2021 | 8 | 2021 |
| K Dokania, P.(2022). An impartial take to the CNN vs transformer robustness contest F Pinto, PHS Torr European conference on computer vision, 466-480, 0 | 6 | |
| Copyright-Protected Language Generation via Adaptive Model Fusion J Abad, K Donhauser, F Pinto, F Yang arXiv preprint arXiv:2412.06619, 2024 | 3* | 2024 |
| Towards Certification of Uncertainty Calibration under Adversarial Attacks C Emde, F Pinto, T Lukasiewicz, PHS Torr, A Bibi arXiv preprint arXiv:2405.13922, 2024 | 3* | 2024 |
| Extracting Training Data From Document-Based VQA Models F Pinto, N Rauschmayr, F Tramèr, P Torr, F Tombari Forty-first International Conference on Machine Learning, 2024 | 3 | 2024 |
| Safewatch: An efficient safety-policy following video guardrail model with transparent explanations Z Chen, F Pinto, M Pan, B Li arXiv preprint arXiv:2412.06878, 2024 | 1 | 2024 |
| As Firm As Their Foundations: Creating Transferable Adversarial Examples Across Downstream Tasks with CLIP A Hu, J Gu, F Pinto, K Kamnitsas, P Torr British Machine Vision Association, 2024 | 1* | 2024 |
| Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models A Hemmat, A Davies, TA Lamb, J Yuan, P Torr, A Khakzar, F Pinto NeurIPS 2024 B&D Track, 2024 | | 2024 |
| Focus On This, Not That! Steering LLMs With Adaptive Feature Specification TA Lamb, A Davies, A Paren, PHS Torr, F Pinto arXiv preprint arXiv:2410.22944, 2024 | | 2024 |
| A Cautionary Tale on the Evaluation of Differentially Private In-Context Learning A Hu, J Guan, P Torr, F Pinto Workshop on Socially Responsible Language Modelling Research, 2024 | | 2024 |
Philip TorrProfessor, University of OxfordVerified email at eng.ox.ac.uk