Kyungmin Min
Scholar

Kyungmin Min

Google Scholar ID: kBeHth0AAAAJ
Ph.D student, Seoul National University
Natural Language ProcessingMultimodal LLMs
Citations & Impact
All-time
Citations
16
 
H-index
2
 
i10-index
1
 
Publications
5
 
Co-authors
0
 
Resume (English only)
Academic Achievements
  • Published multiple papers, including 'Fooling the LVLM Judges: Visual Biases in LVLM-Based Evaluation' accepted to EMNLP 2025, 'Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding' accepted to NAACL 2025 Findings, 'Return of EM: Entity-driven Answer Set Expansion for QA Evaluation' accepted to COLING 2025 (Oral), 'Mitigating Hallucinations in LVLMs via Summary-Guided Decoding' accepted to NeurIPS 2024 SafeGenAI, 'Leveraging Ensemble Techniques and Metadata for Subjective Knowledge-grounded Conversational Systems' awarded Best Paper at DSTC11 workshop.
Research Experience
  • Published papers in several international conferences and participated in research projects such as the DSTC11 challenge for dialogue system technology.
Education
  • Seoul National University, Ph.D. Student in Artificial Intelligence, Advisor: Kyomin Jung, Mar 2023 ~; Sungkyunkwan University, B.S. in Computer Science and Engineering (Magna Cum Laude), Mar 2017 ~ Feb 2023.
Background
  • Ph.D. student at Seoul National University, advised by Prof. Kyomin Jung. Research interests include: enabling LLMs to understand and interact across multiple modalities (Multimodal LLMs), enhancing decoding control for more reliable and precise responses, exploring multi-agent systems to enable dynamic and collaborative AI interactions.
Co-authors
0 total
Co-authors: 0 (list not available)