NAM HYEON-WOO
NAM HYEON-WOO
Embedded Files
I am a final-year PhD candidate at POSTECH (South Korea), advised by Prof. Tae-Hyun Oh.
My research centers on evaluation, analysis, and understanding of models—designing benchmarks and analysis methods that expose model strengths, limitations, and failure modes, turning opaque behavior into actionable signals for debugging and improvement. In some cases, I have taken these analyses a step further, turning the resulting insights into methods that yield concrete performance gains. This work spans first-author publications across top ML venues (ICML, ICLR, NeurIPS, ICCV, ECCV).
I have gained industry and cross-institutional research experience through internships at NAVER AI LAB (mentors: Byeongho Heo, Dongyoon Han, Seong Joon Oh), Helmholtz Munich (Zeynep Akata, Stephan Alaniz), and Amazon (Wenbin Ouyang, Ciprian Adrian Corneanu).
Publications 13 peer-reviewed papers (11 conference and journal, 2 ICML 2026 workshop; 8 as first or co-first author).
Publications 13 peer-reviewed papers (11 conference and journal, 2 ICML 2026 workshop; 8 as first or co-first author).
In-submission
Nam Hyeon-Woo, Wenbin Ouyang, Ciprian Adrian Corneanu, CompJudge: Fine-Grained Comparative Evaluation using Multimodal LLM for Subject-Driven Generation, In submission
Baek Seong-Eun, Nam Hyeon-Woo, Lee Jung-Mok, and Tae-Hyun Oh, Does Visual Arrow Improve Motion Comprehension in Multimodal Large Language Models?, In submission
Moon Ye-Bin, Nam Hyeon-Woo, Baek Seong-Eun, Yejin Yeo, Tae-Hyun Oh, TRAP: Benchmark for Task-completion and Resistance to Active Privacy-extraction, In submission
Wonjun Jo, Nam Hyeon-Woo, Yohan Park, Hyunwoo Ha, Tae-Hyun Oh, When Fine-Tuning Drifts: Mitigating Policy Drift with Base Action-Field Regularization, In submission
Kwon Byung-Ki, Sohwi Lim, Nam Hyeon-Woo, Moon Ye-Bin, Tae-Hyun Oh, Early Failure Detection and Intervention in Video Diffusion Models, In submission
Kim Yu-Ji, Dahye Lee, Kim Jun-Seong, Nam Hyeon-Woo, GeonU Kim, Yongjin Kwon, Yu-Chiang Frank Wang, Jaesung Choe, Tae-Hyun Oh, Enhancing Embodied Reasoning and Grounding by Novel View Synthesis, In submission
Evaluation, analysis, and understanding using LLM, MLLM, or constructing datasets.
Nam Hyeon-Woo, Moon Ye-Bin, Sohwi Lim, Kwon Byung-Ki, Tae-Hyun Oh, Zero-Shot Rankability: Revealing Latent Ordinal Structure in Multimodal Large Language Models via Language, ICML 2026
Nam Hyeon-Woo, Yoonsu Kim, Kihoon Son, Juho Kim, Tae-Hyun Oh, NEMO: Benchmarking Natural-Language Explanations of Vision Model Errors, ICMLW 2026 (Trustworthy AI for Good - AI4GOOD -Workshop)
Nam Hyeon-Woo, Tae-Hyun Oh, Zeynep Akata, Stephan Alaniz, From Numbers to Narratives: Goal-Oriented Summarization of Machine Learning Model Differences, ICMLW 2026 (Workshop on Compositional Learning: Safety, Interpretability, and Agents)
Wonseok Choi, Sohwi Lim, Nam Hyeon-Woo, Moon Ye-Bin, Dong-Ju Jeong, Jinyoung Hwang, Tae-Hyun Oh, Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching, WACV 2026
Nam Hyeon-Woo, Moon Ye-Bin, Wonseok Choi, Lee Hyun, Tae-Hyun Oh, VLM’s Eye Examination: Instruct and Inspect Visual Competency of Vision Language Model, TMLR 2025
Moon Ye-Bin*, Nam Hyeon-Woo*, Wonseok Choi, Tae-Hyun Oh, BEAF: Observing BEfore-AFter Changes to Evaluate Hallucination in Vision-language Models, ECCV, 2024 *equal contribution
Training, Model, Data
Lee Jung-Mok, Nam Hyeon-Woo, Moon Ye-Bin, Junhyun Nam, Tae-Hyun Oh, Automated Model Discovery via Multi-modal & Multi-step Pipeline, NeurIPS 2025
Lee Chae-Yeon, Nam Hyeon-Woo, Tae-Hyun Oh, Learning Correlation-aware Aleatoric Uncertainty for 3D Hand Pose Estimation, BMVC 2025
Do Huu Dat, Nam Hyeon-Woo, Po-Yuan Mao, Tae-Hyun Oh, VSC: Visual Search Compositional Text-to-Image Diffusion Model, ICCV 2025
Moon Ye-Bin*, Nam Hyeon-Woo*, Wonseok Choi, Nayeong Kim, Suha Kwak, Tae-Hyun Oh, SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems, Pattern Recognition Letters (PRL) 2025 *equal contribution
Moon Ye-Bin*, Nam Hyeon-Woo*, Wonseok Choi, Nayeong Kim, Suha Kwak, Tae-Hyun Oh, Exploiting Synthetic Data for Data Imbalance Problems: Baselines from a Data Perspective, ICCV 2023 workshop * equal contribution
Nam Hyeon-Woo, Kim Yu-Ji, Byeongho Heo, Dongyoon Han, Seong Joon Oh, Tae-Hyun Oh, Scratching Visual Transformer's Back with Uniform Attention, ICCV 2023 [project page]
Kwon Byung-Ki, Nam Hyeon-Woo, Ji-Yun Kim, Tae-Hyun Oh, DFlow: Learning to Synthesize Better Optical Flow Datasets via a Differentiable Pipeline, ICLR 2023
Nam Hyeon-Woo, Moon Ye-Bin, and Tae-Hyun Oh, FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning, ICLR 2022
Awards & Honors
Awards & Honors
ICML 2026 Gold Reviewer
Bronze prizes award in Samsung HumanTech 2023 ($5,000 prize)
Scholarship student from SBS Cultural Foundation
Best Poster in POSTECH-Naver AI Day 2022
Qualcomm Innovation Fellowship Korea (QIFK) 2021. Qualcomm Korea AI Research ($4,000 prize)
EDUCATION
EDUCATION
PhD in Electrical Engineering, POSTECH, Pohang, South Korea, (2022.03 - 2026.08)
Master in Electrical Engineering, POSTECH, Pohang, South Korea, (2020.03 - 2022.02)
Bachelor in Electrical Engineering, POSTECH, Pohang, South Korea, (2013 - 2019)
EXPERIENCE
EXPERIENCE
Amazon in Seattle (9.2025 - 3.2026)
EML Lab in Germany (2.2025 - 7.2025)
ML Research team in Naver AI Lab, South Korea, (2.2022 - 8.2022)
Page updated
Google Sites
Report abuse