3 papers
cs.LG2025
Local MDI+: Local Feature Importances for Tree-Based Models
Zhongyuan Liang, Zachary T. Rewolinski, Abhineet Agarwal +2
Tree-based ensembles such as random forests remain the go-to for tabular data over deep learning models due to their prediction performance and computational efficiency. These adva…
cs.LG2025
Adaptive Test-Time Intervention for Concept Bottleneck Models
Matthew Shen, Aliyah Hsu, Abhineet Agarwal +1
Concept bottleneck models (CBM) aim to improve model interpretability by predicting human level "concepts" in a bottleneck within a deep learning model architecture. However, how t…
cs.CL2024
ED-Copilot: Reduce Emergency Department Wait Time with Language Model Diagnostic Assistance
Liwen Sun, Abhineet Agarwal, Aaron Kornblith +2
In the emergency department (ED), patients undergo triage and multiple laboratory tests before diagnosis. This time-consuming process causes ED crowding which impacts patient morta…