When Reasoning Hurts Confidence: Demographic Calibration of Vision-Language Models in Medicine
AAAI/ACM Conference on AI, Ethics, and Society, 2026
Selected Research
Med-REDUCE: Representation Transfer and Efficiency Under Resolution Constraints
Medical Image Analysis, 2026 · *equal contribution
BiasICL: In-Context Learning and Demographic Biases of Vision Language Models
MICCAI, 2025 · *equal contribution
A Framework for Evaluating the Efficacy of Foundation Embedding Models in Healthcare
medRxiv, 2024
Experience
- 2026 ML Engineering Intern, DatologyAI — distributed dataloading and ML infrastructure
- 2025 LLM Guardrails SDE Intern, Amazon — Rufus LLM shopping assistant
- 2025 ZK Research Engineering, Nethermind — post-quantum signature schemes
- 2024 Student Research Fellow, Hoover Institution — technology policy and patent analysis
Open Source
- 2026 torch_measure — a package for AI measurement science
- 2025 condor-rs — Falcon post-quantum signature aggregation with LaBRADOR in Rust, at Nethermind
- 2024 Generative AI for Urban Design — Google Summer of Code with the City of Boston
