Seongheon Park

Hello! I’m a third-year PhD student in the Computer Sciences department at the University of Wisconsin-Madison, where I am fortunate to be advised by Prof. Sharon Li. Previously, I completed my MS degree at Yonsei University in the Electrical and Electronic Engineering department under the supervision of 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.