Hyesong Choi
Hyesong Choi
Assistant Professor in the School of Electronic Engineering at Soongsil University (from 2025.09 -)
Contact
CV / Github / Google Scholar
Email: hyesong@ssu.ac.kr
hyesongchoi2010@gmail.com
I am an assistant professor in the School of Electronic Engineering, College of IT, at Soongsil University, where I lead SAIL (Scalable AI Lab).
My research is committed to advancing intelligent and trustworthy AI systems by understanding both visual and linguistic representations and their interaction with real-world data. I actively work with students across a broad spectrum of topics spanning computer vision and natural language processing.
My recent primary focus is on
(1) improving the efficiency and performance of large-scale Vision-Language Models (VLMs),
with additional research directions including:
(2) AI security, including agentic defensive AI for autonomous security systems and deepfake detection;
(3) large-scale Data filtering and curation for efficient pre-training;
(4) Social AI, focusing on human-centric and socially aware intelligence;
(5) Reinforcement Learning for adaptive and generalizable decision-making systems;
(6) Autonomous driving-related perception and decision-making tasks; and
(7) Generative modeling with Diffusion models.
I obtained my Ph.D. at Ewha W. University in 2025.08, advised by Prof. Dongbo Min. In 2020.03, I obtained my B.S. at Ewha W. University.
I was a research intern at the Backbone Research Group, Naver AI Lab, advised by Dongyoon Han.
News
[2026.03] Granted the NRF Outstanding Early-Career Researcher Program (우수신진연구), funded by the National Research Foundation of Korea (NRF).
[2026.01] CLDA is accepted at ICASSP 2026.
[2026.01] Prof. Hyesong Choi will visit UIUC for two months to conduct collaborative research on Social AI and deepfake detection with Prof. Jim Rehg’s group.
[2025.12] RobIA is accepted at NeurIPS 2025.
[2025.11] Prof. Hyesong Choi has been appointed as a Board Member (학회 이사) of the International Conference on ICT Convergence (ICTC).
[2025.09] Prof. Hyesong Choi joins Soongsil University as an Assistant Professor in the School of Electrical Engineering.
[2025.08] Prof. Hyesong Choi received her Ph.D. in Computer Science and Engineering from Ewha Womans University, with a research focus on large-scale model pre-training, and was awarded the Outstanding Dissertation Award (Graduate School-wide).
Publications (International)
Conference
[C11] CLDA: Collaborative Learning for Unsupervised Enhanced Domain Adaptation
Minhee Cho, Hyesong Choi, Hayeon Jo, and Dongbo Min
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2026
[paper]
[C10] RobIA: Robust Instance-aware Continual Test-time Adaptation for Deep Stereo
Jueun Ko, Hyewon Park, Hyesong Choi, and Dongbo Min
Neural Information Processing Systems (NeurIPS), 2025
[paper / project page / code]
[C9] TADFormer: Task-Adaptive Dynamic TransFormer for Efficient Multi-Task Learning
Seungmin Baek, Soyul Lee, Hayeon Jo, Hyesong Choi, and Dongbo Min
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2025
[paper / project page / code]
[C8] A Simple Framework for Generalization in Visual RL under Dynamic Scene Perturbations
Wonil Song, Hyesong Choi, Kwanghoon Sohn, and Dongbo Min
Neural Information Processing Systems (NeurIPS), 2024
[paper / project page / code]
[C7] Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training
Hyesong Choi, Hyejin Park, Kwang Moo Yi, Sungmin Cha, and Dongbo Min
European Conference on Computer Vision (ECCV), 2024
[paper / project page / code]
[C6] Emerging Property of Masked TOken for Effective Pre-training
Hyesong Choi, Hunsang Lee, Seyoung Joung, Hyejin Park, Jiyeong Kim, and Dongbo Min
European Conference on Computer Vision (ECCV), 2024
[paper / project page / code]
[C5] Environment Agnostic Representation for Visual Reinforcement Learning
Hyesong Choi, Hunsang Lee, Seongwon Jeong, and Dongbo Min
IEEE International Conference on Computer Vision (ICCV), 2023
[paper / project page / code]
[C4] Local-Guided Global: Paired Similarity Representation for Visual Reinforcement Learning
Hyesong Choi, Hunsang Lee, Wonil Song, Sangryul Jeon, Kwanghoon Sohn, and Dongbo Min
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2023
[paper / project page / code]
[C3] KNN Local Attention for Image Restoration
Hunsang Lee, Hyesong Choi, Kwanghoon Sohn, and Dongbo Min
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2022
[paper]
[C2] Sequential Cross Attention Based Multi-Task Learning
Sunkyung Kim, Hyesong Choi, and Dongbo Min
IEEE International Conference on Image Processing (ICIP), 2022
[paper / project page / code]
[C1] Adaptive Confidence Thresholding for Monocular Depth Estimation
Hyesong Choi, Hunsang Lee, Sunok Kim, Seungryoung Kim, and Dongbo Min
IEEE International Conference on Computer Vision (ICCV), 2021
[paper / project page / code]
Journal
[J5] UniTT-Stereo: Unified Training of Transformer for Enhanced Stereo Matching
Soomin Kim, Hyesong Choi, Jihye Ahn, and Dongbo Min
IEEE ACCESS (IF=3.476), 2025
[paper]
[J4] Global Structural Knowledge Distillation for Semantic Segmentation
Hyejin Park, Keonhee Ahn, Hyesong Choi, and Dongbo Min
IEEE ACCESS (IF=3.476), 2025
[paper]
[J3] MaDis-Stereo: Enhanced Stereo Matching via Distilled Masked Image Modeling
Jihye Ahn, Hyesong Choi, Sommin Kim, and Dongbo Min
IEEE ACCESS (IF=3.476), 2025
[paper / project page / code]
[J2] Cross-Scale KNN Image Transformer for Image Restoration
Hunsang Lee, Hyesong Choi, Kwanghoon Sohn, and Dongbo Min
IEEE ACCESS (IF=3.476), 2023
[paper]
[J1] Learning Disentangled Skills for Hierarchical Reinforcement Learning through Trajectory Autoencoder with Weak Labels
Wonil Song, Sangryul Jeon, Hyesong Choi, Kwanghoon Sohn, and Dongbo Min
Expert Systems with Applications (ESWA) (IF=7.5), 2023
[paper]
Preprint
[P10] Isotropic Embedding Perturbations for Robust Vision Language Encoders
Hyesong Choi, Daeun Kim, Song Park, Taekyung Kim, Byeongho Heo, Sangdoo Yun, Dongbo Min, and Dongyoon Han
under review, 2026
[P9] CORE: Corruption-Reconstruction based Data Filtering Network
Hyesong Choi, Daeun Kim, Seungmin Baek, Taekyung Kim, Byeongho Heo, Dongbo Min, and Dongyoon Han
under review, 2026
[P8] ECC: Encoder-Centric Corruption for Fine-Grained Vision in VLMs
Hyesong Choi, Daeun Kim, Sungmin Cha, Kwang Moo Yi, and Dongbo Min
under review, 2026
[P7] Adaptive Noise Injection, Bootstrapping Denoising Diffusion for Generalized Recognition
Hyesong Choi, Daeun Kim, and Dongbo Min
under review, 2026
[P6] Enhancing Alignment for Unified Multimodal Models via Semantically-Grounded Supervision
Jiyeong Kim, Yerim So, Hyesong Choi, Uiwon Hwang, and Dongbo Min
under review, 2026
[P5] Stabilizing Robustness Transfer in Adversarial Distillation with Controlled Teacher Adaptation
Hyejin Park, Hyesong Choi, and Dongbo Min
under review, 2026
[P4] MuCa-ViT: Disentangled and Context-Aware Vision Transformers for Multi-Channel Images
Daeun Kim, Hyejin Park, Hyesong Choi, and Dongbo Min
under review, 2026
[P3] iConFormer: Dynamic Parameter-Efficient Tuning with Input-Conditioned Adaptation
Hayeon Jo, Hyesong Choi, Minhee Cho, and Dongbo Min
arXiv preprint arXiv:2409.02838
[paper]
[P2] SG-MIM: Structured Knowledge Guided Efficient Pre-training for Dense Prediction
Sumin Son, Hyesong Choi, and Dongbo Min
arXiv preprint arXiv:2409.02513
[paper]
[P1] Revisiting augmentation for Contrastive Knowledge Distillation via Comprehending Teacher Intelligence
Jiyeong Kim, Hyesong Choi, Keonhee Ahn, Seongwon Jeong, and Dongbo Min
preprint, 2024
[paper]
Teaching
[2026 Spring] Neural Networks, School of EE & Department of Next-Generation Semiconductor, Soongsil University
(Main Lecturer)
[2026 Spring] Multimedia Convergence Technology, School of EE, Soongsil University
(Main Lecturer)
[2026 Spring] Bio Machine Learning, Department of AI Bio (Graduate School) Soongsil University
(Main Lecturer) - Lectured in English
[2025 Fall] Advanced Programming, School of EE, Soongsil University
(Main Lecturer)
[2025 Spring] Computational Thinking and Programming, CC department, Ewha W. University
(Main Lecturer)
[2024 Fall] Contents Database, CC department, Ewha W. University
(Main Lecturer)
[2024 Spring] Data Innovation and AI Technology, EB department, Seoul Media Institute of Technology - Lectured in English
(Main Lecturer)
Education
M.S./Ph.D. [2020.3 ~ 2025.08] (Advisor: Dongbo Min)
Computer Science
(Outstanding Dissertation Award, Graduate School-wide)
Ewha W. University (EWU)
B.S. [2016.3 ~ 2020.2]
Contents Convergence, Computer Science
(Graduated Summa Cum Laude, rank: 1/n)
Ewha W. University (EWU)
Professional Experience
2026.01 - 2026.02: Visiting Researcher, University of Illinois Urbana-Champaign (UIUC) (Advisor: Jim Rehg, Research topic: Social AI)
2025.03 - 2025.08: Research Intern, Backbone Research Group, Naver AI Lab (Advisor: Dongyoon Han)
2024.09 - 2025.08: Instructor, Ewha W. University (EWU)
(Teaching: Contents Database, Computational Thinking and Programming)
2024.7 - 2024.9: Visiting Researcher, University of British Columbia (UBC) (Advisor: Kwang Moo Yi, Research topic: Generative Pre-Training of Large Vision Models)
2024.3 - 2025.2: Adjunct Professor, Seoul Media Institute of Technology (SMIT)
(Teaching: Data Innovation and AI Technology)
2021.4 - 2022.3: Research Assistant, Hyundai Motors Group
(Project topic: AI-based Automatic Water Inflow Detection Technology to Enhance Vehicle Development Efficiency)
2020.4 - 2021.12: Research Assistant, Institute for Information communication Technology Planning and Evaluation (IITP)
(Project topic: Development of Artificial Intelligence Technology that Continuously Self-improves According to Changing Situations in the Real World)
2020.3 - 2021.2: Research Assistant, National Research Foundation of Korea
(Project topic: Multi-task Learning Model Study for Complementary Scene Understanding based on Depth Estimation and Object Detection/Segmentation)
2018.8 - 2018.12: Research Intern, Action Power
(Research topic: Development of Network Architectures and Augmentation Techniques for Audio Data)
Honor and Award
Outstanding Dissertation Award, Graduate School-wide, 2025
Boeing-Ewha Scholarship, Received Study Incentives (total funding: 4 million KRW), 2025
Distinguished Research Scholarship, Awarded across the entire Graduate School at EWU, 2024
Best Paper Award, Image Processing and Image Understanding, ‘Digging into Semantics in the Mask’, 2023
Solvay Scholarship, Received Tuition and Study Incentives for two years (total funding: 50 million KRW), 2022-2024
Best Paper Award, Image Processing and Image Understanding, ‘Adaptive Confidence Thresholding for Monocular Depth Estimation’, 2020
Best Paper Award, Image Processing and Image Understanding, ‘Pseudo Label-Guided Multitask Learning for Scene Understanding’, 2020
Academic Excellence Award, Ewha W. University, 2016-2020
Major Leadership Scholarship, Ewha W. University, 2016-2020
Samsung SCSC Scholarship, Ewha W. University, 2017-2020
First Prize, Campus Creative Grant Olympiad Startup Contest, ‘Panic disorder cognitive behavioral therapy application development’, 2018
First Prize, New Industry Convergence University Creative Startup Contest, ‘Healing Pet Loss Syndrome using VR’, 2017
Second Prize, New Industry Convergence University Creative Startup Contest, ‘VR Exhibition to visit underprivileged children’, 2016
Academic Services
Conference Reviewer
: CVPR (2022 - present), ICCV (2023 - present), ECCV (2024 - present), NeurIPS (2025-present), ICLR (2026-present)
Journal Reviewer
- Engineering Applications of Artificial Intelligence (EAAI) (IF=8.0)
- International Journal of Computer Vision (IJCV) (IF=9.3)
Society Service
- Board Member, International Conference on ICT Convergence