Paul Yi

Associate Professor, St. Jude Children's Research Hospital

Joined

May 2022

Names

Paul Yi (Preferred)

Emails

****@som.umaryland.edu (Confirmed)

****@jhmi.edu (Confirmed)

****@gmail.com (Confirmed)

****@stjude.org (Confirmed)

Personal Links

Homepage

Google Scholar

Career & Education History

Associate Professor

St. Jude Children's Research Hospital (stjude.org)

2024 – Present

Assistant Professor

University of Maryland, Baltimore (umaryland.edu)

2021 – 2024

Advisors, Relations & Conflicts

No relations added

Expertise

Radiology AI

2017 – Present

Publications

[Short] Downstream Effects of Translation Scale with Language Difficulty
Aditya V. Kulkarni, Dharmam Savani, Ammar Ahmed Pallikonda Latheef, Pritam Mukherjee, Jacob M Luber, Paul Yi
- ICLR 2026 Workshop DATA-FM
- Readers: Everyone
Optimal Large Language Model Characteristics to Balance Accuracy and Energy Use for Sustainable Medical Applications
Florence Xini Doo, Dharmam Savani, Adway Kanhere, Ruth Carlos, Anupam Joshi, Paul Yi, Vishwa Sanjay Parekh
- Radiology
- Readers: Everyone
Multiaccuracy and Multicalibration via Proxy Groups
Beepul Bharti, Mary Versa Clemens-Sewall, Paul Yi, Jeremias Sulam
- ICML 2025 poster
- Readers: Everyone
Towards Resource-Efficient Streaming of Large-Scale Medical Image Datasets for Deep Learning
Pranav Kulkarni, Adway Kanhere, Eliot Siegel, Paul Yi, Vishwa Sanjay Parekh
- MIDL 2025 Poster
- Readers: Everyone
Care to Explain? AI Explanation Types Differentially Impact Chest Radiograph Diagnostic Performance and Physician Trust in AI
Drew Prinster, Amama Mahmood, Suchi Saria, Jean Jeudy, Cheng Ting Lin, Paul Yi, Chien-Ming Huang
- Radiology
- Readers: Everyone
Sufficient and Necessary Explanations (and What Lies in Between)
Beepul Bharti, Paul Yi, Jeremias Sulam
- CPAL 2025 (Proceedings Track) Oral
- Readers: Everyone
Sufficient and Necessary Explanations (and What Lies in Between)
Beepul Bharti, Paul Yi, Jeremias Sulam
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Improving Multi-Center Generalizability of GAN-Based Fat Suppression using Federated Learning
Pranav Kulkarni, Adway Kanhere, Harshita Kukreja, Vivian Zhang, Paul Yi, Vishwa Sanjay Parekh
- MIDL 2024 Short Papers
- Readers: Everyone
Anytime, Anywhere, Anyone: Investigating the Feasibility of Segment Anything Model for Crowd-Sourcing Medical Image Annotations
Pranav Kulkarni, Adway Kanhere, Dharmam Savani, Andrew Chan, Devina Chatterjee, Paul Yi, Vishwa Sanjay Parekh
- MIDL 2024 Short Papers
- Readers: Everyone
Hidden in Plain Sight: Undetectable Adversarial Bias Attacks on Vulnerable Patient Populations
Pranav Kulkarni, Andrew Chan, Nithya Navarathna, Skylar Chan, Paul Yi, Vishwa Sanjay Parekh
- MIDL 2024 Oral
- Readers: Everyone

View all 12 publications

Co-Authors

View all 27 co-authors