Seewon Choi

최시원

CIS PhD @ UPenn

Hi, I'm a third year PhD student in Computer and Information Science at the University of Pennsylvania, advised by Rajeev Alur.

My research focuses on developing trustworthy AI models through neurosymbolic approaches, which combine neural learning with symbolic reasoning. I work on scaling these methods to complex, real-world scenarios and applying them in clinical settings. Currently, I am using these approaches for the early diagnosis of critical conditions, ensuring that predictions are grounded in clinical knowledge.

Previously, I received my Bachelor's degree from the University of Cambridge, where I worked on rep2rep with Mateja Jamnik.

Updates

[Dec 25] I will be presenting CTSketch @ NeurIPS 2025

[Dec 24] I will be presenting ISED @ NeurIPS 2024

[Jun 24] I will be attending PLDI 2024

Preprints

• KardiaLM: A Foundation Model for ECG Comprehension

Neelay Velingker*, S Choi*, Mayank Keoliya*, Alaia Solko-Breslin*, Rajeev Alur, Mayur Naik, Eric Wong

• Stable Prediction of Adverse Events in Medical Time-Series Data

Mayank Keoliya*, S Choi*, Rajeev Alur, Mayur Naik, Eric Wong

Publications

• CTSketch: Compositional Tensor Sketching for Scalable Neurosymbolic Learning

S Choi*, Alaia Solko-Breslin*, Rajeev Alur, Eric Wong

NeurIPS 2025

• Data Efficient Learning with Neural Programs

Alaia Solko-Breslin, S Choi, Ziyang Li, Neelay Velingker, Rajeev Alur, Mayur Naik, Eric Wong

NeurIPS 2024

• Generation of Visual Representations for Multi-Modal Mathematical Knowledge

Lianlong Wu*, S Choi*, Daniel Raggi*, Aaron Stockdill, Grecia Garcia Garcia, Fiorenzo Colarusso, Peter C.H. Cheng, Mateja Jamnik

AAAI 2024 Demo