Israel Mason-Williams

PhD Researcher in Safe and Trusted AI
Israel is a scholar of artificial intelligence - finding innovative and creative solutions for issues surrounding trust, bias, transparency and safety to support a synergy between development and fairness. He has studied at the University of Cambridge where he received a distinction for his M.Phil. and is currently at Kings and Imperial working under the Safe and Trusted AI CDT.

He has published research at world class AI conferences 1x ICLR, 2x NeurIPS and 4x ICML.

He currently works as a PhD student in the nascent field of mechanistic interpretability to understand and control AI, his work draws inspiration from many fields to develop beautiful yet effective solutions to some of the biggest problems in AI. Israel is also highly involved in the emerging regulatory and policy landscape of AI representing the UK as a Talos Fellow for the EU and recently has begun exploring how to maximise his research impact via startup streams with the incredible support from the visionaries at 50Y and ConceptionX.

Life Updates:

Jun 6, 2025

Paper accepted at the first Workshop on Technical AI Governance at ICML exploring the role of Reproducibility and AI Governance.

Jun 1, 2025

Attended the Oxford AI Gala supported by Athropic.

Mar 27, 2025
Mar 01, 2025

Joined cohort 8 of ConceptionX.

Mar 01, 2025

Joined the first UK cohort of 50 Years (50Y).

Dec 10, 2024

Attended NeurIPS 2024 and presented work on understanding knowledge distillation and geometric properties of neural networks.

Nov 11, 2024

Awarded the Simms Prize for Eductaional Achievement from Lucy Cavendish College at The University of Cambridge.

Oct 03, 2024

Joined UKRI Safe and Trusted AI CDT as a PhD Student.

May 07, 2024

Attended ICLR 2024 and presented work on understanding neural network compression.

Oct 03, 2023

Joined the University of Cambridge to study an M.Phil. in Advanced Computer Science.

Jul 25, 2023

Graduated from Queen Mary University of London with First Class Honours in Computer Science.

Sept 12, 2022

Joined the Eurpean Bioinformatics Institute to research protein function prediction with ML/AI.