DAMTP ML for Science Reading Group


2025-10-28 15:30: An Introduction to Mechanistic Interpretability (Rachel C. Zhang (DAMTP PhD), Liz Tan (DAMTP PhD))

2025-11-04 15:30: Mechanistic interpretability (cont.) + reasoning in LLMs (Chris Chiu (University of Cambridge))

2025-11-11 15:30: Image Restoration without Clean Data, RL for Particle Physics (Troy Vu; Yong Sheng Koay )

2025-11-18 15:30: Automated Scientific Discovery with ML Review, Can We Interpret the Quality of NNs without Testing? (Yi Gu (DAMTP PhD), Luca Muscarnera (DAMTP PhD))

2025-11-25 15:30: Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning (Dr. Miles Cranmer (DAMTP/IoA Assistant Prof.)  )

2026-02-04 11:00: The interpretability wars (Rachel C. Zhang (DAMTP PhD))

2026-02-11 11:00: The State of AI in 2026 (Liz Tan (University of Cambridge))

2026-02-18 11:00: AI Advances in Protein Folding and Variant Effect Prediction (Caroline Pier (University of Cambridge))

2026-02-25 11:00: Key Ideas in Quantum Machine Learning (Rakesh Achutha, University of Cambridge)

2026-03-04 11:00: Overview on the AI scientists and scientific discovery (Chris Chiu (University of Cambridge))

2026-03-11 11:00: How Do Language Models Reason and Compute? A Mechanistic Interpretability Approach (Julia Dima (DIS MPhil))

2026-03-18 11:00:  AI Alignment & RL in Turbulent Environments (Leo Thom (Uni of Cambridge), Yixuan Zhu (Imperial Col.))