| Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks T Räuker, A Ho, S Casper, D Hadfield-Menell arXiv preprint arXiv:2207.13243, 2022 | 190 | 2022 |
| Linearly structured world representations in maze-solving transformers M Ivanitskiy, AF Spies, T Räuker, G Corlouer, C Mathwin, L Quirke, ... Proceedings of UniReps: the First Workshop on Unifying Representations in …, 2024 | 8* | 2024 |
| A configurable library for generating and manipulating maze datasets MI Ivanitskiy, R Shah, AF Spies, T Räuker, D Valentine, C Rager, L Quirke, ... arXiv preprint arXiv:2309.10498, 2023 | 4 | 2023 |
| Transformers Use Causal World Models in Maze-Solving Tasks AF Spies, W Edwards, MI Ivanitskiy, A Skapars, T Räuker, K Inoue, ... arXiv preprint arXiv:2412.11867, 2024 | | 2024 |
Alexander F. SpiesCS Ph.D. Candidate, Imperial College LondonEmail được xác minh tại imperial.ac.uk