You can also find my articles on my Google Scholar profile.
Published in NeurIPS 2023 UniReps Workshop, 2023
Transformers trained to solve mazes form linear representations of maze structure, and acquire interpretable attention heads which facilitate path-following.
Ivanitskiy, M.I.*, Spies, A.F.*, Räuker, T.* et al. Structured World Representations in Maze-Solving Transformers. NeurIPS 2023 UniReps Workshop. [BIB] [PDF]
Published in arXiv preprint, 2023
A dataset to generate simple Maze-like environments for use with Transformers.
Ivanitskiy, M.I., Shah, R., Spies, A.F. et al. A Configurable Library for Generating and Manipulating Maze Datasets. arXiv, 10.48550/arXiv.2309.10498 (2023). [BIB] [PDF]
Published in ICML Dynn Workshop (Spotlight), 2022
Assessing the extent to which sparsity and structured (Obect-Centric) representations are beneficial for neural relational reasoning.
Spies, A.F., Russo, A., Shanahan, M. (2022). Sparse Relational Reasoning with Object-Centric Representations. ICML 2022 DyNN Workshop. [BIB] [PDF]
Published in Journal of Instrumentation, 2019
Investigating the potential use of charge sharing between neighboring pixels in HEP sensors to increase resolution and radiation hardness.
Nachman, B. & Spies, A.F. (2019). Nonlocal Thresholds for Improving the Spatial Resolution of Pixel Detectors. Journal of Instrumentation. [BIB] [PDF]