Publications
Publications by categories in reversed chronological order.
2025
-
Rashomon Sets for Prototypical-Part Networks: Editing Interpretable Models in Real-TimeIn Proceedings of the Computer Vision and Pattern Recognition Conference, 2025 -
This EEG Looks Like These EEGs: Interpretable Interictal Epileptiform Discharge Detection With ProtoEEG-kNNIn Conference on Medical Image Computing and Computer Assisted Intervention, 2025 -
Creating interpretable deep learning models to identify species using environmental DNA sequencesScientific Reports, 2025 -
-
How your location relates to health: Variable importance and interpretable machine learning for environmental and sociodemographic dataIn Proceedings of the AAAI Conference on Artificial Intelligence, 2025 -
-
It’s LIT! Reliability-Optimized LLMs with Inspectable ToolsIn 39th Conference on Neural Information Processing Systems (NeurIPS 2025)Workshop: Workshop on Multi-Turn Interactions in Large Language Models, 2025 -
Doctor Rashomon and the UNIVERSE of Madness: Variable Importance with Unobserved Confounding and the Rashomon EffectarXiv preprint arXiv:2510.12734, 2025
2024
-
AsymMirai: Interpretable Mammography-Based Deep Learning Model for 1–5-Year Breast Cancer Risk PredictionRadiology, 2024 -
Interpretable Image Classification with Adaptive Prototype-based Vision TransformersIn Advances in Neural Information Processing Systems, 2024 -
This Looks Better Than That: Better Interpretable Models with ProtoPNextarXiv preprint arXiv:2406.14675, 2024 -
FPN-IAIA-BL: A Multi-Scale Interpretable Deep Learning Model for Classification of Mass Margins in Digital MammographyIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024 -
Interpretable generalized additive models for datasets with missing valuesAdvances in Neural Information Processing Systems, 2024 -
Position: Amazing Things Come From Having Many Good ModelsIn International Conference on Machine Learning, 2024
2023
-
The Rashomon Importance Distribution: Getting RID of Unstable, Single Model-Based Variable ImportanceAdvances in Neural Information Processing Systems, 2023 -
ProtoEEGNet: An Interpretable Approach for Detecting Interictal Epileptiform DischargesIn Medical Imaging Meets NeurIPS, 2023
2022
-
Deformable ProtoPNet: An Interpretable Image Classifier using Deformable PrototypesIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022