Seongheon Park

Hello! I’m a third-year Ph.D. student in the Department of Computer Sciences at the University of Wisconsin-Madison, where I am fortunate to be advised by Prof. Sharon Li. Previously, I received my M.S. and B.S. degrees in Electrical and Electronic Engineering from Yonsei University, where I was advised by Prof. Kwanghoon Sohn and Prof. Kibok Lee.

My research focuses on making foundation models (LLMs, LVLMs, and VLAs) safe and reliable in real-world deployment. Specifically, I study why and how these models fail and how to monitor and correct them through:

• Failure detection, mitigation, and recovery
• Failure reasoning and diagnosis
• Latent-space interpretability

These are crucial for preventing catastrophic failures in human-facing and industrial applications, and for enabling robust agentic systems to stop, replan, and incorporate human intervention in an interpretable way. I am also broadly interested in multimodal models and post-training.