[Apr 6, 2026] New preprint: BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence [arXiv] [code] [project], work led by Sean Wu.
[Mar 24, 2026] New preprints: Semantic Self-Distillation for Language Model Uncertainty [arXiv] [project] and Entropy Alone is Insufficient for Safe Selective Prediction in LLMs [arXiv] [project], work led by Edward Phillips.
[Mar 11, 2026] New preprint: SignalMC-MED: A Multimodal Benchmark for Evaluating Biosignal Foundation Models on Single-Lead ECG and PPG [arXiv] [code] [project].