collaborators

5 papers

cs.CR2025

Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated

Hanna Foerster, Ilia Shumailov, Yiren Zhao +4

Early research into data poisoning attacks against Large Language Models (LLMs) demonstrated the ease with which backdoors could be injected. More recent LLMs add step-by-step reas…

physics.comp-ph2025

Hybrid Physics-Machine Learning Models for Quantitative Electron Diffraction Refinements

Shreshth A. Malik, Tiarnan A. S. Doherty, Benjamin Colmey +3

High-fidelity electron microscopy simulations required for quantitative crystal structure refinements face a fundamental challenge: while physical interactions are well-described t…

cs.LG2025

Leveraging Deep Learning for Physical Model Bias of Global Air Quality Estimates

Kelsey Doerksen, Yuliya Marchetti, Kevin Bowman +5

Air pollution is the world's largest environmental risk factor for human disease and premature death, resulting in more than 6 million permature deaths in 2019. Currently, there is…

cs.LG2025

Uncertainty Quantification for Surface Ozone Emulators using Deep Learning

Kelsey Doerksen, Yuliya Marchetti, Steven Lu +5

Air pollution is a global hazard, and as of 2023, 94\% of the world's population is exposed to unsafe pollution levels. Surface Ozone (O3), an important pollutant, and the drivers…

q-bio.QM2025

Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction

Ruben Weitzman, Peter Mørch Groth, Lood Van Niekerk +4

Retrieving homologous protein sequences is essential for a broad range of protein modeling tasks such as fitness prediction, protein design, structure modeling, and protein-protein…