About Me

I graduated from the Georgia Institute of Technology with a B.S. in Computer Engineering in 2021. After completing my undergraduate studies, I decided to continue my education and pursue a Ph.D. in the field of Artificial Intelligence/Deep Learning at the Korea Advanced Institute of Science and Technology (KAIST). I am currently working under the guidance of Professor Chang D. Yoo, whose expertise and leadership have been invaluable to my research.

My current research interest lies in fundamentally enhancing the spatial intelligence and reasoning dynamics of Vision-Language Models (VLMs). Within this scope, my current work investigates whether modern VLMs possess the capacity to imagine within a visual space, internally simulating or representing visual information to solve complex spatial problems. I aim to move beyond standard image-text alignments to better understand and improve how these models process spatial relationships and visual transformations.

---

Work Experience

• Microsoft Research Asia (MSRA), Beijing, China
  Research Intern, Visual Computing Group
  July 2025 - Dec. 2025 (expected)
  Advisors: Chong Luo and Qi Dai

---

Education

• Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea
  Ph.D. candidate (integrated) in Electrical Engineering (Artificial Intelligence/Deep Learning)
  Aug. 2021 - Present
  Advisor: Chang D. Yoo




• Georgia Institute of Technology, Atlanta, GA, United States
  B.S. in Computer Engineering
  graduated May 2021
  Cumulative GPA: 3.92/4.0 (highest honors)

---

Publications

* denotes equal contribution
denotes selected publications
[C]: Conference Paper [W]: Workshop Paper [J]: Journal Paper

• [C20] PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning
  Hee Suk Yoon*, Eunseop Yoon*, Ji Woo Hong, SooHwan Eom, Gwanhyeong Koo, Mark Hasegawa-Johnson, Qi Dai, Chong Luo, Chang D. Yoo
  CVPR 2026
  




• [C19] Diffusion Negative Preference Optimization Made Simple
  Joshua Tian Jin Tee, Hee Suk Yoon, Sunjae Yoon, Tri Ton, Chang D. Yoo
  ICLR 2026
  




• [C18] TESSAR: Geometry-Aware Active Regression via Dynamic Voronoi Tessellation
  Seong Jin Cho, Gwangsu Kim, Junghyun Lee, Hee Suk Yoon, Joshua Tian Jin Tee, Chang D. Yoo
  ICLR 2026
  




• [C17] A Gradient Guidance Perspective on Stepwise Preference Optimization for Diffusion Models
  Joshua Tian Jin Tee, Hee Suk Yoon, Abu Hanif Muhammad Syarubany, Eunseop Yoon, Chang D. Yoo
  Neurips 2025
  




• [C16] ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization
  Hee Suk Yoon, Eunseop Yoon, Mark Hasegawa-Johnson, Sungwoong Kim, Chang D. Yoo
  ICML 2025
  [arxiv]




• [C15] Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models
  Eunseop Yoon*, Hee Suk Yoon*, Mark Hasegawa-Johnson, Chang D. Yoo
  ICLR 2025
  [paper]




• [C14] BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation
  Hee Suk Yoon*, Eunseop Yoon*, Joshua Tian Jin Tee*, Kang Zhang, Yu-Jung Heo, Du-Seong Chang, Chang D. Yoo
  ECCV 2024
  [arxiv]




• [ J1] Physics Informed Distillation for Diffusion Models
  Joshua Tian Jin Tee*, Kang Zhang*, Hee Suk Yoon, Dhananjaya Nagaraja Gowda, Chanwoo Kim, Chang D. Yoo
  TMLR 2024
  [paper] [code]




• [C13] LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition
  Eunseop Yoon*, Hee Suk Yoon*, John Harvill, Mark Hasegawa-Johnson, Chang D. Yoo
  INTERSPEECH 2024 (oral)
  [paper] [arxiv]




• [C12] TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback
  Eunseop Yoon*, Hee Suk Yoon*, SooHwan Eom*, Gunsoo Han, Daniel Wontae Nam, Daejin Jo, Kyoung-Woon On, Mark Hasegawa-Johnson, Sungwoong Kim, Chang D. Yoo
  ACL 2024 (findings)
  [paper] [arxiv] [code]




• [C11] C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
  Hee Suk Yoon*, Eunseop Yoon*, Joshua Tian Jin Tee, Mark Hasegawa-Johnson, Yingzhen Li, Chang D. Yoo
  ICLR 2024
  [paper] [arxiv] [code] [poster] [slides]




• [C10] ADAMER-CTC: Connectionist Temporal Classification with Adaptive Maximum Entropy Regularization for Automatic Speech Recognition
  SooHwan Eom, Eunseop Yoon, Hee Suk Yoon, Chanwoo Kim, Mark Hasegawa-Johnson, Chang D. Yoo
  ICASSP 2024
  [paper] [arxiv] [poster]




• [C9] SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation
  Hyun Ryu, Sunjae Yoon, Hee Suk Yoon, Eunseop Yoon, Chang D. Yoo
  AAAI 2024
  [paper] [arxiv] [code]




• [C8] HEAR: Hearing Enhanced Audio Response for Video-grounded Dialogue
  Sunjae Yoon, Dahyun Kim, Eunseop Yoon, Hee Suk Yoon, Junyeong Kim, Chang D. Yoo
  EMNLP 2023 (findings)
  [paper] [arxiv] [code]




• [W2] One-Shot and Few-Shot Exemplification Modeling
  John Harvill, Hee Suk Yoon, Eunseop Yoon, Mark Hasegawa-Johnson and Chang D. Yoo
  EMNLP 2023 Workshop on Generation, Evaluation & Metrics (GEM 2023)
  [paper]




• [C7] Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction
  Eunseop Yoon*, Hee Suk Yoon*, Dhananjaya Gowda, SooHwan Eom, Daehyeok Kim, John Harvill, Heting Gao, Mark Hasegawa-Johnson, Chanwoo Kim, Chang D. Yoo
  INTERSPEECH 2023
  [paper] [arxiv] [poster]




• [W1] One-Shot Exemplification Modeling via Latent Sense Representations
  John Harvill, Hee Suk Yoon, Eunseop Yoon, Mark Hasegawa-Johnson and Chang D. Yoo
  ACL 2023 Workshop on Representation Learning for NLP (RepL4NLP 2023)
  [paper] [poster]




• [C6] INTapt: Information-Theoretic Adversarial Prompt Tuning for Enhanced Non-Native Speech Recognition
  Eunseop Yoon*, Hee Suk Yoon*, John Harvill, Mark Hasegawa-Johnson, Chang D. Yoo
  ACL 2023 (findings)
  [paper] [arxiv]




• [C5] ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure
  Hee Suk Yoon*, Joshua Tian Jin Tee*, Eunseop Yoon, Sunjae Yoon, Gwangsu Kim, Yingzhen Li, Chang D. Yoo
  ICLR 2023
  [paper] [arxiv] [poster] [code]




• [C4] Counterfactual Two-stage Debiasing for Video Corpus Moment Retrieval
  Sunjae Yoon, Ji Woo Hong, SooHwan Eom, Hee Suk Yoon, Eunseop Yoon, Daehyeok Kim, Junyeong Kim, Chanwoo Kim, Chang D. Yoo
  ICASSP 2023 (oral)
  [paper]




• [C3] SMSMix: Sense Maintained Sentence Mixup for Word Sense Disambiguation
  Hee Suk Yoon*, Eunseop Yoon*, John Harvill, Sunjae Yoon, Mark Hasegawa-Johnson, Chang D. Yoo
  EMNLP 2022 (findings)
  [paper] [arxiv]




• [C2] Information-Theoretic Text Hallucination Reduction for Video-grounded Dialogue
  Sunjae Yoon, Eunseop Yoon, Hee Suk Yoon, Junyeong Kim, Chang D. Yoo
  EMNLP 2022
  [paper] [arxiv] [poster]




• [C1] Selective Query-Guided Debiasing for Video Corpus Moment Retrieval
  Sunjae Yoon, Ji Woo Hong, Eunseop Yoon, Dahyun Kim, Junyeong Kim, Hee Suk Yoon, Chang D. Yoo
  ECCV 2022
  [paper] [arxiv] [code]

---

Academic Activities

Award

• Excellent Paper Award, 2024 Summer Conference of the Korean Artificial Intelligence Association: 2024.08.15

Invited Talk

• CAU-AI Core Technology Seminar (Navigating Uncertainty Challenges in Classification and Language Generation): 2024.03.22

Journal Reviewing

• Transactions on Machine Learning Research (TMLR)

Conference Reviewing

• International Conference on Machine Learning (ICML): 2025

• International Conference on Learning Representations (ICLR): 2025

• Conference on Neural Information Processing Systems (Neurips): 2024

• IEEE International Workshop on Machine Learning for Signal Processing (MLSP) 2024

• 9th Workshop on Representation Learning for NLP (RepL4NLP) 2024

• European Conference on Computer Vision (ECCV): 2024

• Conference on Computer Vision and Pattern Recognition (CVPR): 2024, 2025

• Association for Computational Linguistics Rolling Review (ARR): 2024

• Association for Computational Linguistics (ACL): 2023

• International Conference on Acoustics, Speech & Signal Processing (ICASSP): 2023, 2024, 2025

• Empirical Methods on Natural Language Processing (EMNLP): 2022, 2023

• International Conference on Learning Representations Tiny Papers Track (ICLR TinyPapers): 2024

Teaching Assistance

• Statistical Learning Theory 2024 Spring

• Introduction to Machine Learning 2023 Fall, 2024 Fall

• Introduction to Reinforcement Learning 2023 Spring

• Signals and Systems 2022 Spring, 2022 Fall

• Hwaseong City-KAIST Semiconductor Specialized Curriculum - Large Language Models 2023

• Seongnam-KAIST Next Generation ICT Research Center EE Co-op+ Joint Research Program 2023 Fall

• Seongnam-KAIST Next Generation ICT Research Center Machine Learning and Big Data Course: 2021, 2022, 2023

---