THE RAJPURKAR LAB

Building the autonomy stack for medicine.

Simulators, agents, and robots that move medical AI from prediction to action.

HARVARD MEDICAL SCHOOL · EST. 2021

PUBLISHED IN

Nature ·Nature Medicine ·Nature Biotechnology ·Cell ·The Lancet ·NEJM AI ·JACC ·Radiology

Towards generalizable AI in medicine via Generalist–Specialist Collaboration Nature Biomedical Engineering, 1-15, 2026 ReXSonoVQA: A Video QA Benchmark for Procedure-Centric Ultrasound Understanding arXiv preprint arXiv:2604.10916, 2026 Opportunistic Cardiovascular Risk Assessment Using Routine Head CT in the Emergency Department JACC, 2026 MedVersa: A Generalist Foundation Model for Diverse Medical Imaging Tasks NEJM AI 3 (4), AIoa2500595, 2026 Generalist biological artificial intelligence in modeling the language of life Nature Biotechnology, 1-16, 2026 ReXInTheWild: A Unified Benchmark for Medical Photograph Understanding arXiv preprint arXiv:2603.19517, 2026 A clinical environment simulator for dynamic AI evaluation Nature medicine, 1-8, 2026 Unifying the odyssey: artificial intelligence for rare disease diagnosis and therapy Health and Technology, 1-12, 2026 CRIMSON: A Clinically-Grounded LLM-Based Metric for Generative Radiology Report Evaluation MICCAI 2026 The Doctor Will Agree With You Now: Sycophancy of Large Language Models in Multi-Turn Medical Conversations Proceedings of the 1st Workshop on Linguistic Analysis for Health (HeaLing …, 2026 Towards generalizable AI in medicine via Generalist–Specialist Collaboration Nature Biomedical Engineering, 1-15, 2026 ReXSonoVQA: A Video QA Benchmark for Procedure-Centric Ultrasound Understanding arXiv preprint arXiv:2604.10916, 2026 Opportunistic Cardiovascular Risk Assessment Using Routine Head CT in the Emergency Department JACC, 2026 MedVersa: A Generalist Foundation Model for Diverse Medical Imaging Tasks NEJM AI 3 (4), AIoa2500595, 2026 Generalist biological artificial intelligence in modeling the language of life Nature Biotechnology, 1-16, 2026 ReXInTheWild: A Unified Benchmark for Medical Photograph Understanding arXiv preprint arXiv:2603.19517, 2026 A clinical environment simulator for dynamic AI evaluation Nature medicine, 1-8, 2026 Unifying the odyssey: artificial intelligence for rare disease diagnosis and therapy Health and Technology, 1-12, 2026 CRIMSON: A Clinically-Grounded LLM-Based Metric for Generative Radiology Report Evaluation MICCAI 2026 The Doctor Will Agree With You Now: Sycophancy of Large Language Models in Multi-Turn Medical Conversations Proceedings of the 1st Workshop on Linguistic Analysis for Health (HeaLing …, 2026

210+ papers · 53713+ citations · h-index 55 · Google Scholar

OBSERVE · REASON · ACT — the autonomy stack, demonstrated.

2026

2025

2024

2023

Sourced from Google Scholar. Updated 2026-05-21.

Recent venues: Nature · Nature Medicine · Nature Biotech · Cell · The Lancet · NEJM AI · JACC · Radiology

See all 100+ papers → /publications

OBSERVE

Perception models and benchmarks for medical imaging, video, and clinical signals.

e.g. MedVersa · NEJM AI · 2026

ACT

Procedural understanding and supervised autonomy in physical medical AI.

e.g. ReXSonoVQA · CHIL · 2026

THE TEAM

Pranav + a compact team across clinical AI, simulation, robotics, and medical validation. → Meet the lab.

We don't just publish papers.
We build the people who
will lead the field.

MEDICAL AI BOOTCAMP · HARVARD · STANFORD · MIT

Apply →

JOIN