NeurIPS 2026 Workshop on Medical Reasoning with Vision Language Foundation Models (Med-Reasoner)

Introduction

Vision-language foundation models demonstrate strong performance in pattern recognition, but lack robust reasoning capabilities, limiting their application in specialized domains. Medical imaging highlights this critical limitation: diagnosis requires connecting visual findings with clinical knowledge through explicit reasoning processes. While foundation models excel at visual recognition, medical decision-making demands interpretable chain-of-thought diagnosis, multimodal grounding of visual features in clinical knowledge, comprehensive evaluation frameworks for reasoning quality, and probabilistic reasoning for clinical decisions. Given the rapid advancements in foundation models over the past three years, addressing these reasoning gaps has become essential for deploying AI systems in high-stakes healthcare applications where explainability and trustworthiness are paramount.

The NeurIPS 2026 Workshop on Medical Reasoning with Vision Language Foundation Models (Med-Reasoner) aims to bring together computer vision researchers, medical AI experts, imaging scientists, and practicing clinicians to discuss state-of-the-art advancements, applications, and challenges in reasoning capabilities for medical vision-language models. The workshop will foster discussions that inspire innovation in interpretable medical AI and address real-world deployment challenges including privacy constraints, workflow integration into healthcare systems, and ensuring fairness across patient populations.

Invited Speakers

Jason Fries, PhD

Stanford University

Mike Schaekermann, PhD

Google Health

Shalmali Joshi, PhD

Columbia University

Michael Moor, PhD

ETH Zurich

Sam Schmidgall

Johns Hopkins University

Muhammad Mamdani, PharmD

University of Toronto
University Health Network

📑 Accepted Papers

Accepted papers will be announced after the review process.

🗓️ Workshop Schedule

Time	Session
09:00 – 09:15	Opening Framing the open problems (organizer intro)
09:15 – 10:00	Invited Talk 1 Jason Fries, PhD Stanford University
10:00 – 10:45	Invited Talk 2 Mike Schaekermann, PhD Google Health
10:45 – 11:15	☕ Coffee + Posters
11:15 – 12:00	Invited Talk 3 Shalmali Joshi, PhD Columbia University
12:00 – 12:45	Invited Talk 4 Michael Moor, PhD ETH Zurich
12:45 – 14:00	🍽️ Lunch
14:00 – 14:45	Invited Talk 5 Sam Schmidgall Johns Hopkins University
14:45 – 15:30	Invited Talk 6 Muhammad Mamdani, PharmD University of Toronto · University Health Network
15:30 – 16:00	Spotlights Contributed Spotlights 3 × 8 min + Q&A
16:00 – 16:30	☕ Coffee + Posters All accepted papers
16:30 – 17:30	🎙️ Panel + Audience Debate "What does it mean to evaluate reasoning, and what should the community standardize?"
17:30 – 17:45	Community Open-Problem Synthesis & Closing

Organizers

Anas Zafar

Research Associate
MD Anderson Cancer Center

Sana Tonekaboni, PhD

Postdoctoral Fellow
Broad Institute of MIT and Harvard

Min Woo Sun

PhD Candidate
Stanford University

Julia Vogt, PhD

Associate Professor
ETH Zurich

Jia Wu, PhD

Associate Professor
MD Anderson Cancer Center

Alejandro Lozano