Showing 1–20 of 110 results
/ Date/ Name
Oct 13, 2018ClinicalVis: Supporting Clinical Task-Focused Design EvaluationMar 20, 2017The Use of Autoencoders for Discovering Patient PhenotypesAug 8, 2016Uncovering Voice Misuse Using Symbolic MismatchOct 19, 2022"Why did the Model Fail?": Attributing Model Performance Changes to Distribution ShiftsMay 29, 2025MedPAIR: Measuring Physicians and AI Relevance Alignment in Medical Question AnsweringDec 13, 2024Generative AI in MedicineNov 7, 2024BendVLM: Test-Time Debiasing of Vision-Language EmbeddingsMay 23, 2017Clinical Intervention Prediction and Understanding using Deep NetworksMay 8, 2022Write It Like You See It: Detectable Differences in Clinical Notes By Race Lead To Differential Model RecommendationsDec 2, 2021Learning Optimal Predictive ChecklistsSep 23, 2020Probabilistic Machine Learning for HealthcareFeb 14, 2020CheXclusion: Fairness gaps in deep chest X-ray classifiersFeb 17, 2025What's in a Query: Polarity-Aware Distribution-Based Fair RankingNov 1, 2024Identifying Implicit Social Biases in Vision-Language ModelsJun 16, 2025Bias Delayed is Bias Denied? Assessing the Effect of Reporting Delays on Disparity AssessmentsJun 9, 2025KScope: A Framework for Characterizing the Knowledge Status of Language ModelsFeb 6, 2025Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple InteractionsJun 9, 2025When Style Breaks Safety: Defending LLMs Against Superficial Style AlignmentMay 23, 2017Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning ApproachMar 17, 2022Semi-Markov Offline Reinforcement Learning for Healthcare