Publications, Reports, & Blogs

Some of my written work, varying from reports and blogs to actual papers.

Ferreira, A. (2025). A Warning Sign for the Use of Safety Evaluations in Policy Making [Working Paper]. Centre for International Governance Innovation Digital Policy Hub. Coming soon!

Ferreira, A., Mahip, S., Capra, A., Carli, I., Duque Quiceno, D., Fedorko, W. T., Fujiwara, M., Li, M., Martin, L., Saito, Y., Smith, G., Xu, A. (2025). Antimatter Annihilation Vertex Reconstruction with Deep Learning for ALPHA-g Radial Time Projection Chamber [Journal article]. Journal of High Energy Physics. Available on arXiv and JHEP.

Heesters, N., Chemaly, D., Muller, O., Sola, E., Fabbro, S., Ferreira, A., McConnachie, A., Magnier, E., Hudson, M., Chambers, K., Hammer, F., Sanchez-Janssen R. (2025). Galaxies OBserved as Low-luminosity Identified Nebulae (GOBLIN): Catalog of 43 000 high-probability dwarf galaxy candidates in the UNIONS survey [Journal article]. Astronomy & Astrophysics. Available on arXiv and A&A.

Ferreira, A. (2025). Are LLMs Actually Getting Safer? [Working Paper]. Centre for International Governance Innovation Digital Policy Hub. Access.

Ferreira, A., Mahip, S., Capra, A., Carli, I., Duque Quiceno, D., Fedorko, W. T., Fujiwara, M., Li, M., Martin, L., Saito, Y., Smith, G., Xu, A. (2024). AI Meets Antimatter: Unveiling Antihydrogen Annihilations [Workshop paper]. Machine Learning and the Physical Sciences Workshop at NeurIPS 2024. Available on arXiv and workshop website.

Ferreira, A., Mahip, S., Capra, A., Carli, I., Duque Quiceno, D., Fedorko, W. T., Fujiwara, M., Li, M., Martin, L., Saito, Y., Smith, G., Xu, A. (2024). ALPHA-g Preprocessed Simmulation Dataset for Machine Learning [Dataset]. Zenodo. Access.

Ferreira, A. (2024). Illuminating the Ultraviolet Near Infrared Optical Northern Survey with Simple Masked Image Modeling [PHYS 437B report]. Access.\(^1\)

Ferreira, A. (2023). Applying Self-Supervised Representation Learning to the Ultraviolet Near Infrared Optical Northern Survey [PHYS 437A report]. Access.\(^1\)

Ferreira, A (2023) Implications of Explainable of Artificial Intelligence to the Ethics of Automated Warfare [Policy brief]. University of Waterloo Defence and Security Foresight Group AI, Ethics, and Warfare Series Publications. Access. (Note: looking back, I see many ways to criticize this paper…)

Sun, Y., & Ferreira, A. (2023). [Scientific report]. Defence Research and Development Canada Research Reports.

Ferreira, A (2023). Can Artificial Intelligence Bots Sail Better than Humans? [Medium blog]. UWaterloo Data Science Medium Page. Access.\(^2\)

\(^1\) PHYS 437 is the fourth-year research project in the Department of Physics and Astronomy at the University of Waterloo. For this project I was co-supervised by Sebastien Fabbro from the Herzberg Astronomy & Astrophysics Research Centre and Mike Hudson from the University of Waterloo.

\(^2\) This blog post has 52 claps (analogous to likes) and counting!