Seongheon Park
Contact. seongheon_park [at] cs [dot] wisc [dot] edu
1210 W Dayton St
Madison, WI 53706
Hello! I’m a first-year PhD student in the Computer Sciences department at the University of Wisconsin-Madison, where I am fortunate to be advised by Prof. Sharon Yixuan 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.
I am broadly interested in safe and reliable machine learning that align with human intentions and values. Currently, my research focuses on the safety of Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs).
news
| Jul 02, 2025 | Our paper about LVLM object hallucnation detection is accepted by ICML 2025 Workshop on Reliable and Responsible Foundation Models  |
|---|---|
| May 01, 2025 | Two papers are accepted by ICML 2025  |
| Apr 02, 2025 | Two papers are accepted by ICLR 2025 Workshop: Quantify Uncertainty and Hallucination in Foundation Models  |
| Sep 01, 2024 | I’ve started my PhD journey at UW-Madison!  |
| Mar 16, 2024 | Our paper Rethinking Open-World Semi-Supervised Learning: Distribution Mismatch and Inductive Inference is accepted by CVPR Workshop 2024.  |
publications
- ICML Workshop
GLSim: Detecting Object Hallucinations in LVLMs via Global-Local SimilarityICML 2025 Workshop on Reliable and Responsible Foundation Models, Jul 2025 - Preprint
Shaking to Reveal: Perturbation-Based Detection of LLM HallucinationsarXiv:2506.02696, Jun 2025 - Preprint
GeoRanker: Distance-Aware Ranking for Worldwide Image GeolocalizationarXiv:2505.13731, May 2025 - ICML
Steer LLM Latents for Hallucination DetectionInternational Conference on Machine Learning, May 2025 - ICML
Position: Challenges and Future Directions of Data-Centric AI AlignmentInternational Conference on Machine Learning, May 2025 - ICLR Workshop
Can Your Uncertainty Scores Detect Hallucinated Entity?ICLR Workshop: Quantify Uncertainty and Hallucination in Foundation Models, Mar 2025 - CVPR Workshop
Rethinking Open-World Semi-Supervised Learning: Distribution Mismatch and Inductive InferenceCVPR Workshop on Computer Vision in the Wild, Jun 2024 - ICCV
Hierarchical visual primitive experts for compositional zero-shot learningIEEE/CVF International Conference on Computer Vision, Oct 2023 - CVPR
Partmix: Regularization strategy to learn part discovery for visible-infrared person re-identificationIEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2023 - WACV
Normality guided multiple instance learning for weakly supervised video anomaly detectionIEEE/CVF Winter Conference on Applications of Computer Vision, Jan 2023 - WACV
Language-free training for zero-shot video groundingIEEE/CVF Winter Conference on Applications of Computer Vision, Jan 2023
