Published:
Internal Microsoft MLADS presentation on explainable machine learning work during a Microsoft Ireland internship.
Recommended citation: Tyrolski, M. (2022). Explainable machine learning at Microsoft MLADS (Internal Microsoft MLADS Conference presentation).
Download Paper | Download Slides
Published:
Study of evaluation pitfalls in MHC-I presentation prediction, with a unified methodology and model for peptide-MHC-I binding.
Recommended citation: Giziński, S., Preibisch, G., Kucharski, P., Tyrolski, M., Rembalski, M., Grzegorczyk, P., & Gambin, A. (2024). Enhancing antigenic peptide discovery: Improved MHC-I binding prediction and methodology. Methods, 224, 1–9. https://doi.org/10.1016/j.ymeth.2024.01.016
Download Paper | Download Slides
Published in NAACL 2022, 2022
Hourglass adds downsampling and upsampling to Transformers for more efficient long-sequence modeling; evaluated on ImageNet32 and enwik8.
Recommended citation: Nawrot, P., Tworkowski, S., Tyrolski, M., Kaiser, Ł., Wu, Y., Szegedy, C., & Michalewski, H. (2022). Hierarchical transformers are more efficient language models. Findings of the Association for Computational Linguistics: NAACL 2022, 1559-1571.
Download Paper | Download Slides
Published in ICLR 2023 (Top-5%, Oral), 2023
AdaSubS adjusts planning horizon using generated subgoals and reachability filtering; evaluated on Sokoban, Rubik’s Cube, and INT.
Recommended citation: Zawalski, M., Tyrolski, M., Czechowski, K., Odrzygóźdź, T., Stachura, D., Piękos, P., Wu, Y., Kuciński, Ł., & Miłoś, P. (2022). Fast and precise: Adjusting planning horizon with adaptive subgoal search. arXiv preprint arXiv:2206.00702.
Download Paper | Download Slides
Published in ICLR 2024 (Generative Models for Decision Making), 2024
Empirical study of when hierarchical search helps in combinatorial reasoning, with evaluation guidelines for comparing methods.
Recommended citation: Zawalski, M., Góral, G., Tyrolski, M., Wiśnios, E., Budrowski, F., Cygan, M., Kuciński, Ł., & Miłoś, P. (2024). What matters in hierarchical search for combinatorial reasoning problems? arXiv preprint arXiv:2406.03361.
Download Paper | Download Slides
Published in CoRL 2025 workshop, 2025
Benchmark, toolkit, and live leaderboard for evaluating VLM temporal progress estimation in robotics videos; supports automated dataset curation.
Recommended citation: Budzianowski, P., Wiśnios, E., Tyrolski, M., Góral, G., Kulakov, I., Petrenko, V., & Walas, K. (2025). OpenGVL--Benchmarking Visual Temporal Progress for Data Curation. arXiv preprint arXiv:2509.17321.
Download Paper | Download Slides
Published in bioRxiv 2026, 2026
bioRxiv preprint on data contamination in T-cell epitope discovery; reframes MHC-I prediction as protein-centric learning to rank.
Recommended citation: Preibisch, G., Tyrolski, M., Kucharski, P., Giziński, S., Grzegorczyk, P., Moon, S., Kim, S., Zaro, B., & Gambin, A. (2026). Resolution of recursive data corruption to transform T-cell epitope discovery. bioRxiv, 2026.03.30.710191. https://doi.org/10.64898/2026.03.30.710191
Download Paper | Download Slides