Area of research
Artificial Intelligence · Health Informatics
Research interest
Research interests include Algorithms and Data Compression, Artificial Intelligence in Healthcare and Education, Topic Modeling, and Parallel Computing and Optimization Techniques.
An AI system to help scientists write expert-level empirical software
Advancing conversational diagnostic AI with multimodal reasoning.
Accelerating scientific discovery with Co-Scientist.
Towards Better Health Conversations: The Benefits of Context-seeking
Toward expert-level medical question answering with large language models.
Towards conversational diagnostic artificial intelligence.
Towards accurate differential diagnosis with large language models.
Collaboration between clinicians and vision-language models in radiology report generation.
A unified acoustic-to-speech-to-language embedding space captures the neural basis of natural language processing in everyday conversations
Observation of constructive interference at the edge of quantum ergodicity
A unified acoustic-to-speech-to-language embedding space captures the neural basis of natural language processing in everyday conversations.
A personal health large language model for sleep and fitness coaching.
Triaging mammography with artificial intelligence: an implementation study.
Temporal structure of natural language processing in the human brain corresponds to layered hierarchy of large language models
Generative AI for medical education: Insights from a case study with medical students and an AI tutor for clinical reasoning
Temporal structure of natural language processing in the human brain corresponds to layered hierarchy of large language models.
Advancing Conversational Diagnostic AI with Multimodal Reasoning
Evaluating medical AI systems in dermatology under uncertain ground truth
An AI system to help scientists write expert-level empirical software
Towards Generalist Biomedical AI
Using generative AI to investigate medical imagery models and datasets
A toolbox for surfacing health equity harms and biases in large language models.
Health equity assessment of machine learning performance (HEAL): a framework and dermatology AI model case study
Global prediction of extreme floods in ungauged watersheds.
Conversational AI in health: Design considerations from a Wizard-of-Oz dermatology case study with users, clinicians and a medical LLM
An intentional approach to managing bias in general purpose embedding models
Prospective Multi-Site Validation of AI to Detect Tuberculosis and Chest X-Ray Abnormalities.
Consensus, dissensus and synergy between clinicians and specialist foundation models in radiology report generation
Large language models encode clinical knowledge.
UniTune: Text-Driven Image Editing by Fine Tuning a Diffusion Model on a Single Image