Talk with Neel Nanda (Google DeepMind)

On Friday 6th November Neel Nanda is returning to Oxford to give a talk. Neel leads the mechanistic interpretability team at Google DeepMind and will give an overview of interpretability and how it can and cannot help AI safety. 

Measuring the roughness of a signal
 Cont, R Das, P (04 Oct 2026)
Do Higher-Order Models Win for Higher-Order Reasons? Rethinking Performance Gains in Hypergraph Learning
 Bu, F Li, F Lee, G Kim, S Wang, X Lambiotte, R Shin, K (06 Oct 2026)
Social Physics: A manifesto
 Kertész, J Barthelemy, M Caldarelli, G Chakrabarti, B Di Matteo, T Galam, S Gonzales, M Holovatch, Y Holyst, J Jalan, S Jeong, H Johnson, N Lambiotte, R Lü, L Lux, T Mantegna, R Perc, M Saramäki, J Small, M Takayasu, M Yasseri, T Zhou, W (07 Oct 2026)
Community-Centers Identify Robust Biomarkers in High-Dimensional, Low-Sample-Size Gene Expression Data
 Li, R Bai, T Lambiotte, R Levy, O Expert, P Li, D Havlin, S (11 Oct 2026)
A Gauge-Invariant Clustering Coefficient for Complex-Weighted Bipartite Networks
 Waghmare, A Tian, Y Lambiotte, R (08 Oct 2026)
Properties of hypersurface singular sets of solutions to the σk-Yamabe equation in the negative cone
 Duncan, J Nguyen, L Discrete & Continuous Dynamical Systems
Subscribe to