Nandi Schoots

Nandi Schoots

About Me

I’m searching for research questions that cut to the core of human understanding and hope to one day find natural laws that make highly specific predictions and apply in many contexts. In the mean-time I’m working on a variety of projects that piqued my interest.

I am an FLI postdoctoral researcher in Alessandro Abate’s OXCAV group at the University of Oxford. Previously, I did my PhD in the STAI group under supervision of Peter McBurney (King’s College London) and Murray Shanahan (Imperial College London, DeepMind).

I was one of the main organizers of the first AI Safety Camp.

Interests

Science of Deep Learning and (Implicit) Inductive Biases in Neural Networks
Machine Unlearning and Activation Steering
Societal Impacts of AI and AI Safe

Recent Publications

Nandi Schoots, Mattia Jacopo Villani, Niels Uit De Bos (2025). Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks . AISTATS.

Nandi Schoots, Alex Jackson, Ali Kholmovaia, Peter McBurney, Murray Shanahan (2024). The Propensity for Density in Feed-forward Models . ECAI.

Nicholas Pochinkov, Nandi Schoots (2024). Dissecting Language Models: Machine Unlearning via Selective Pruning . SoLaR @NeurIPS.

Yohan Mathew, Ollie Matthews, Robert McCarthy, Joan Velja, Christian Schroeder De Witt, Dylan Cope, Nandi Schoots (2024). Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs .

Teun Van Der Weij, Massimo Poesio, Nandi Schoots (2023). Extending Activation Steering to Broad Skills and Multiple Behaviours .

Ole Jorgensen, Dylan Cope, Nandi Schoots, Murray Shanahan (2023). Improving Activation Steering in Language Models with Mean-Centring . Responsible Language Models @AAAI.

Mattia Jacopo Villani, Nandi Schoots (2023). Any Deep ReLU Network is Shallow . ECAI.

Alex Jackson, Nandi Schoots, Amin Ahantab, Michael Luck, Elizabeth Black (2023). Finding Sparse Initialisations using Neuroevolutionary Ticket Search (NeTS). In ALIFE.