Hyunwoo Oh

About

I am a Ph.D. candidate at Hanyang University, advised by Prof. Dong-Jin Kim in the MMAI Lab. My research interests include geometry-aware deep learning, diffusion models, generative models, computer vision, and multimodal learning.

Research Keywords: Geometry-aware Deep Learning, Diffusion Models, Generative Models, Computer Vision, Multimodal Learning

Publications

* denotes equal contribution. Full list on Google Scholar.

2026

C.6

Adaptive Auxiliary Prompt Blending for Target-Faithful Diffusion Generation

Kwanyoung Lee, SeungJu Cha, Yebin Ahn, Hyunwoo Oh, Sungho Koh, Dong-Jin Kim

CVPR 2026

Paper

C.5

FollowtheSaliency representative method figure

Follow the Saliency: Supervised Saliency for Retrieval-augmented Dense Video Captioning

Seung hee Choi, MinJu Jeon, Hyunwoo Oh, Jihwan Lee, Dong-Jin Kim

CVPR 2026

Paper

C.4

ADAPT: Attention Driven Adaptive Prompt Scheduling and InTerpolating Orthogonal Complements for Rare Concepts Generation

Kwanyoung Lee, Hyunwoo Oh, SeungJu Cha, Sungho Koh, Dong-Jin Kim

CVPR Findings 2026

Paper

2025

J.3

Combining near-infrared... representative method figure

Combining near-infrared spectroscopic signatures and physical traits based on machine vision to enhance accuracy in identification of the geographical origins of agricultural products

Seongsoo Jeong, Seung-hee Choi, Hyunwoo Oh, Haejin Kim, Han-sub Chang, Jisook Song, Ho jin Kim, Dong-Jin Kim, Hoeil Chung

Microchemical Journal 2025

Paper

J.2

FlawMatch: Conditional Defect Image Generation via Flow Matching for Improved Surface Defect Classification

Hyunwoo Oh, Seunghee Choi, Jinho Baek, Dong-Jin Kim, Junegak Joung

AEI 2025 First Author

Paper

C.3

ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion

Sungho Koh, SeungJu Cha, Hyunwoo Oh, Kwanyoung Lee, Dong-Jin Kim

NeurIPS 2025

Paper Code

C.2

CatchPhrase representative method figure

CatchPhrase: EXPrompt-Guided Encoder Adaptation for Audio-to-Image Generation

Hyunwoo Oh, SeungJu Cha, Kwanyoung Lee, Si-Woo Kim, Dong-Jin Kim

ACM MM 2025 First Author

Paper

C.1

VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness

SeungJu Cha, Kwanyoung Lee, Ye-Chan Kim, Hyunwoo Oh, Dong-Jin Kim

CVPR 2025

Paper

2020

J.1

Speaker Anonymization... representative method figure

Speaker Anonymization for Personal Information Protection Using Voice Conversion Techniques

In-Chul Yoo, Keonnyeong Lee, Seonggyun Leem, Hyunwoo Oh, Bonggu Ko, Dongsuk Yook

IEEE Access 2020

Paper

Education & Experience

Ph.D. Candidate

Hanyang University Sep 2023 - Present

MMAI Lab · Advisor: Prof. Dong-Jin Kim

M.S. in Computer Science

Korea University Mar 2018 - Feb 2020

GPA 4.37/4.50 · Advisor: Prof. Dongsuk Yook

B.S. in Computer Science

Sangmyung University Mar 2014 - Feb 2018

GPA 3.61/4.50

Research Engineer

Saltlux AI Labs Jan 2022 - Jun 2023

Audio-Image Multimodal Researcher · Alternative Military Service Program

Research Engineer

FXGear Apr 2020 - Jan 2022

Audio-Image Multimodal Researcher · Alternative Military Service Program

Honors & Grants

32nd Samsung HumanTech Paper Awards (Honorable Mention, Co-Author) — Samsung Electronics , 2026

SoC Taekwon Robot Division (Silver Prize) — International Robot Contest , 2017

HURO-Competition (Bronze Prize) — Intelligent SoC Robot War , 2017

Asia Regional (Honorable Mention) — ACM International Collegiate Programming Contest , 2016

Asia Regional (Honorable Mention) — ACM International Collegiate Programming Contest , 2015

Academic Service

Reviewer: 2025 - NeurIPS; 2026 - CVPR, ECCV, NeurIPS; 2027 - AAAI.