Tom Stepleton
Google (United States)(US)Google DeepMind (United Kingdom)(GB)
Publications by Year
Research Areas
Ethics and Social Impacts of AI, Reinforcement Learning in Robotics, Adversarial Robustness in Machine Learning, Privacy-Preserving Technologies in Data, Advanced Causal Inference Techniques
Most-Cited Works
- → Taxonomy of Risks posed by Language Models(2022)518 cited
- → Ethical and social risks of harm from Language Models(2021)71 cited
- → A General Approach to Fairness with Optimal Transport(2020)42 cited
- → Wasserstein Fair Classification(2019)38 cited
- → Q($λ$) with Off-Policy Corrections(2016)23 cited
- → Gaps in the Safety Evaluation of Generative AI(2024)12 cited
- → Counterfactual Credit Assignment in Model-Free Reinforcement Learning(2020)8 cited
- → Q($$\lambda $$) with Off-Policy Corrections(2016)7 cited
- → Neural Encoding of Scene Statistics for Surface and Object Inference(2009)4 cited