CVPR 2025

• Date: June 11–15, 2025

• Location: Nashville TN

Event Overview

Two members of the PathFinder Lab (Sangjeong Ahn, Hyeseong Lee) attended the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025), the world’s leading event in the field of computer vision. The conference gathered over 41,000 authors and 12,000 reviewers, with 2,872 papers accepted from 13,008 submissions. Our participation focused on gaining insights into the latest advances in computer vision, medical AI, and foundation models, as well as networking with leading global researchers.

Program Participation

Workshop Sessions:

• Foundation Models for Medical Vision: Gained insights into the latest research trends from leading groups including Kather Lab (pioneers in pathology LLMs) and Faisal Mahmood Lab (leaders in foundation models for pathology).

• Medical Computer Vision: Engaged with cutting-edge work from the renowned startup Paige and Stony Brook University’s CVLab, known for their diffusion model research in digital pathology.

Main Conference Sessions:

• Attended sessions across key computer vision domains, including generative models, representation learning, medical image analysis, and vision-language models.

Key Outcomes

• Successfully invited Prof. Faisal Mahmood to speak at the upcoming REG Challenge event hosted by our lab

• Established academic exchange with researchers from the Stony Brook CVLab

• Sparked new research ideas relevant to Hyeseong Lee’s current work on pathology image restoration

Impact

Participation in CVPR 2025 significantly deepened our lab’s understanding of the state-of-the-art in medical AI and foundation model development. Interaction with world-leading researchers and exposure to frontier research strengthened the direction of our ongoing projects.