Nandi Schoots - RankMe

23 papers A* 1A 4Journal 15Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	Punctuations and Predicates in Language Models. EACL (Findings) Sonakshi Chauhan, Maheep Chaudhary, Kwan Kiu Choy, Samuel Nellessen, Nandi Schoots
2026	J	`jnl`	Soft Contamination Means Benchmarks Test Shallow Generalization. CoRR Ari Spiesberger, Juan J. Vazquez, Nicky Pochinkov, Tomas Gavenciak, Peli Grietzer, Gavin Leech, Nandi Schoots
2025	A	`conf`	Any ReLU Network Is Shallow. ECAI Mattia Jacopo Villani, Nandi Schoots
2025	—	`conf`	Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs. IJCNLP-AACL (long papers) Yohan Mathew, Ollie Matthews, Robert McCarthy, Joan Velja, Christian Schröder de Witt, Dylan Cope, Nandi Schoots
2025	J	`jnl`	Modular Training of Neural Networks aids Interpretability. CoRR Satvik Golechha, Maheep Chaudhary, Joan Velja, Alessandro Abate, Nandi Schoots
2025	J	`jnl`	Open Problems in Mechanistic Interpretability. CoRR Lee Sharkey, Bilal Chughtai, Joshua Batson, Jack Lindsey, Jeff Wu, Lucius Bushnaq, Nicholas Goldowsky-Dill, Stefan Heimersheim, Alejandro Ortega, Joseph Isaac Bloom, Stella Biderman, Adrià Garriga-Alonso, Arthur Conmy, Neel Nanda, Jessica Rumbelow, Martin Wattenberg, Nandi Schoots, Joseph Miller, Eric J. Michaud, Stephen Casper, Max Tegmark, William Saunders, David Bau, Eric Todd, Atticus Geiger, Mor Geva, Jesse Hoogland, Daniel Murfet, Tom McGrath
2025	J	`jnl`	Open Problems in Mechanistic Interpretability. Trans. Mach. Learn. Res. Lee Sharkey, Bilal Chughtai, Joshua Batson, Jack Lindsey, Jeffrey Wu, Lucius Bushnaq, Nicholas Goldowsky-Dill, Stefan Heimersheim, Alejandro Ortega, Joseph Isaac Bloom, Stella Biderman, Adrià Garriga-Alonso, Arthur Conmy, Neel Nanda, Jessica Rumbelow, Martin Wattenberg, Nandi Schoots, Joseph Miller, William Saunders, Eric J. Michaud, Stephen Casper, Max Tegmark, David Bau, Eric Todd, Atticus Geiger, Mor Geva, Jesse Hoogland, Daniel Murfet, Tom McGrath
2025	J	`jnl`	Punctuation and Predicates in Language Models. CoRR Sonakshi Chauhan, Maheep Chaudhary, Koby Choy, Samuel Nellessen, Nandi Schoots
2025	A	`conf`	Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks. AISTATS Nandi Schoots, Mattia Jacopo Villani, Niels uit de Bos
2025	J	`jnl`	Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks. CoRR Nandi Schoots, Mattia Jacopo Villani, Niels uit de Bos
2024	A	`conf`	Channel Randomisation Methods for Zero-Shot Communication. ECAI Dylan Cope, Nandi Schoots
2024	J	`jnl`	Dissecting Language Models: Machine Unlearning via Selective Pruning. CoRR Nicholas Pochinkov, Nandi Schoots
2024	J	`jnl`	Extending Activation Steering to Broad Skills and Multiple Behaviours. CoRR Teun van der Weij, Massimo Poesio, Nandi Schoots
2024	J	`jnl`	Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs. CoRR Yohan Mathew, Ollie Matthews, Robert McCarthy, Joan Velja, Christian Schröder de Witt, Dylan Cope, Nandi Schoots
2024	A	`conf`	The Propensity for Density in Feed-Forward Models. ECAI Nandi Schoots, Alex Jackson, Ali Kholmovia, Peter McBurney, Murray Shanahan
2024	J	`jnl`	The Propensity for Density in Feed-forward Models. CoRR Nandi Schoots, Alex Jackson, Ali Kholmovaia, Peter McBurney, Murray Shanahan
2023	A*	`conf`	A theory of representation learning gives a deep generalisation of kernel methods. ICML Adam X. Yang, Maxime Robeyns, Edward Milsom, Ben Anson, Nandi Schoots, Laurence Aitchison
2023	J	`jnl`	Any Deep ReLU Network is Shallow. CoRR Mattia Jacopo Villani, Nandi Schoots
2023	J	`jnl`	Comparing Optimization Targets for Contrast-Consistent Search. CoRR Hugo Fry, Seamus Fallows, Ian Fan, Jamie Wright, Nandi Schoots
2023	J	`jnl`	Improving Activation Steering in Language Models with Mean-Centring. CoRR Ole Jorgensen, Dylan Cope, Nandi Schoots, Murray Shanahan
2023	J	`jnl`	Low-Entropy Latent Variables Hurt Out-of-Distribution Performance. CoRR Nandi Schoots, Dylan Cope
2021	J	`jnl`	Learning to Communicate with Strangers via Channel Randomisation Methods. CoRR Dylan Cope, Nandi Schoots
2021	—	`conf`	Safety Properties of Inductive Logic Programming. SafeAI@AAAI Gavin Leech, Nandi Schoots, Joar Skalse