Hee Suk Yoon
Scholar

Hee Suk Yoon

Google Scholar ID: eJ_iOQEAAAAJ
PhD candidate @ KAIST
Deep LearningNatural Language ProcessingAudioVision-LanguageUncertainty
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
242
 
H-index
8
 
i10-index
8
 
Publications
20
 
Co-authors
0
 
Contact
Emailhskyoon@kaist.ac.krCVOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
7 items
High-Fidelity Text-to-Image Generation from Pre-Trained Vision-Language Models via Distribution-Conditioned Diffusion Decoding
2026
Cited
0
PACR: Progressively Ascending Confidence Reward for LLM Reasoning
2025
Cited
0
Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models
2025
Cited
0
ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Large Language Model Preference Optimization
2025
Cited
0
HEAR: Hearing Enhanced Audio Response for Video-grounded Dialogue
Conference on Empirical Methods in Natural Language Processing · 2023
Cited
6
SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation
AAAI Conference on Artificial Intelligence · 2023
Cited
1
Selective Query-Guided Debiasing for Video Corpus Moment Retrieval
European Conference on Computer Vision · 2022
Cited
20
Resume (English only)
Academic Achievements
  • [C17] A Gradient Guidance Perspective on Stepwise Preference Optimization for Diffusion Models, Neurips 2025
  • [C16] ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization, ICML 2025
  • [C15] Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models, ICLR 2025
  • [BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation, ECCV 2024
  • [J1] Physics Informed Distillation for Diffusion Models, TMLR 2024
  • [C13] LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition, INTERSPEECH 2024 (oral)
  • [C12] TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback, ACL 2024 (findings)
  • [C11] C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion, ICLR 2024
  • [C10] ADAMER-CTC: Connectionist Temporal Classification with Adaptive Maximum Entropy Regularization for Automatic Speech Recognition, ICASSP 2024
Research Experience
  • Microsoft Research Asia (MSRA), Beijing, China - Research Intern, Visual Computing Group, July 2025 - Dec. 2025 (expected), Advisors: Chong Luo and Qi Dai
Education
  • 1. Korea Advanced Institute of Science and Technology (KAIST) - Ph.D. candidate (integrated) in Electrical Engineering (Artificial Intelligence/Deep Learning), Aug. 2021 - Present, Advisor: Chang D. Yoo
  • 2. Georgia Institute of Technology - B.S. in Computer Engineering, graduated May 2021, Cumulative GPA: 3.92/4.0 (highest honors)
Background
  • Research Interests: The reliability of AI/Deep Learning technologies for various modalities, including images, videos, and natural language. Professional Field: Computer Engineering. Background: Graduated from Georgia Institute of Technology, currently pursuing a Ph.D. at KAIST, advised by Professor Chang D. Yoo.
Miscellany
  • Personal Interests: Staying up-to-date with the latest developments in the field of AI/DL, as well as reading and learning about other areas of computer science and engineering.
Co-authors
0 total
Co-authors: 0 (list not available)