I am a Staff ML Researcher and Engineer at PathAI in Boston, with a focus on foundation models, multimodal methods, robustness to distribution shifts and applications of ML in real-world systems. Some examples of past work -
- Novel ML methods research -
- Foundation Models - PLUTO: a scalable & performant Foundation Model for pathology (accepted in following workshops in ICML 2024 - ML for life and material science, Foundation models in the wild and Accessible and efficient foundation models for biological discovery )
- Domain generalization - ContriMix (Best-performing official submission in Camelyon17 Stanford WILDS leaderboard)
- Label Imbalance - Supervised Contrastive MIL (WACV 2024)
- Interpretability - Additive Multiple Instance Learning (NeurIPS 2022)
- Interpretability analysis on a pathology foundation model reveals biologically relevant embeddings across modalities (ICML Mechanistic Interpretability Workshop 2024)
- Application of ML to medical imaging -
-
Clinical trials for liver disease - AI-based automation of enrollment criteria and endpoint assessment in clinical trials in liver diseases (Nature Medicine 2024)
- ML Evaluation - Rethinking ML model evaluation in pathology (ICLR ML Evaluation Standards Workshop 2022)
- ML to predict clinically significant portal hypertension in NASH cirrhosis - Journal of Hepatology
-
- Talks and interviews -
- PyTorch Conference 2023 - Lightning talk on domain generalization in medical imaging
- ML Seminar Series, University of Minnesota - AI for digital pathology
- Fung Institute of Engineering Leadership, UC Berkeley - Alumnus interview
Posts
-
How to think with images
-
Observations on self-supervised learning for vision
-
Foundation models for vision
subscribe via RSS