Joe Benton
Publications by Year
Research Areas
Generative Adversarial Networks and Image Synthesis, Model Reduction and Neural Networks, Adversarial Robustness in Machine Learning, Explainable Artificial Intelligence (XAI), Rocket and propulsion systems research
Most-Cited Works
- → Design and Manufacture of a Propellant Tank Assembly(2007)8 cited
- → A Continuous Time Framework for Discrete Denoising Models(2022)7 cited
- → Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming(2025)5 cited
- → Design & Manufacture of a High Performance High Mass Efficient Gas Tank for the Vega Avum(2007)5 cited
- → From denoising diffusions to denoising Markov models(2024)5 cited
- → Reasoning Models Don't Always Say What They Think(2025)4 cited
- → Polysemanticity and Capacity in Neural Networks(2022)4 cited
- → Many-shot Jailbreaking(2024)3 cited
- → Error Bounds for Flow Matching Methods(2023)3 cited
- → Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety(2025)2 cited