EDUCATION
Ph.D., School of Electrical & Electronic Engineering, Yonsei university (2013. 08)
B. S., School of Electrical & Electronic Engineering, Yonsei university (2008. 02)
ACADEMIC EMPLOYMENT
Professor, Yonsei university (2026. 03 ~ Present)
Associate Professor, Yonsei university (2021. 03 ~ 2026.02)
Assistant Professor, Yonsei university (2016. 09 ~ 2021.02)
Associate Editor, International Journal of Computer Vision (2019. 09 ~ Present)
Area Chair - CVPR 2022, 2024, 2025, 2026 (Lead AC), ICCV 2023 (Workshop Chair), 2025, ECCV 2024
Postdoctoral Research Fellow, INRIA Paris, École Normale Supérieure (ENS), CNRS (2014. 05 ~ 2016. 06)
Research Assistant, University of Illinois at Urbana-Champaign (UIUC) (2012. 09 ~ 2012. 12)
RESEARCH INTEREST
Computer Vision
Deep Learning
AWARD
Silver prize, 32nd Samsung Human-Tech Prize on Signal Processing (2026)
IEIE/IEEE Joint Award for Young Scientist and Engineer (2022)
Silver prize, 28th Samsung Human-Tech Prize on Signal Processing (2022)
Gold prize, 27th Samsung Human-Tech Prize on Signal Processing (2021)
Silver prize, 26th Samsung Human-Tech Prize on Signal Processing (2020)
Silver prize, 25th Samsung Human-Tech Prize on Signal Processing (2019)
Distinguished Research Award, Yonsei University (2019)
Grand Prize, Chun-Gang Outstanding Research Award (2014)
Certificate of Merit, Yonsei University Thesis Award Spring (2013)
Grand prize, Qualcomm Innovation Fellowship (2012)
Honor prize, 17th Samsung Human-Tech Prize on Signal Processing (2011)
SELECTED PUBLICATIONS
Jeimin Jeon, Hyunju Lee, and Bumsub Ham
TAS-LoRA: Transformer Architecture Search with Mixture-of-LoRA Experts
IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun., 2026
Youngmin Oh, Changjae Oh, and Bumsub Ham
PROTO-SAGA: Prototype-Based 3D Scene Segmentation with Semantic-Aware Gaussian Grouping
IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Findings (CVPR Findings), Jun., 2026
Sanghoon Lee, Geon Lee, Hyekang Park, and Bumsub Ham
Exploring Hierarchical Consistency and Unbiased Objectness for Open-Vocabulary Object Detection
IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Findings (CVPR Findings), Jun., 2026
Jaehyeon Moon and Bumsub Ham
Shift-and-Sum Quantization for Visual Autoregressive Models
Int. Conf. Learning Representations (ICLR), Apr., 2026
Byunggwan Son*, Jeimin Jeon*, Jeongwoo Choi*, and Bumsub Ham
Relational Feature Caching for Accelerating Diffusion Transformers
Int. Conf. Learning Representations (ICLR), Apr., 2026
Wonjun Lee*, Haon Park*, Doehyeon Lee, Bumsub Ham, and Suhyun Kim
Jailbreaking on Text-to-Video Models via Scene Splitting Strategy
Int. Conf. Learning Representations (ICLR), Apr., 2026
Seunghoon Lee*, Jeongwoo Choi*, Byunggwan Son, Jaehyeon Moon, Jeimin Jeon, and Bumsub Ham
AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models
Adv. Neural Inf. Process. Syst. (NeurIPS), Dec., 2025
Junghyup Lee*, Jeimin Jeon*, Dohyung Kim, and Bumsub Ham
Scheduling Weight Transitions for Quantization-Aware Training
IEEE/CVF Int. Conf. Comput. Vis. (ICCV), Oct., 2025
Wonjun Lee*, Doehyeon Lee*, Eugene Choi, Sangyoon Yu, Ashkan Yousefpour, Haon Park, Bumsub Ham, and Suhyun Kim
ELITE: Enhanced Language-Image Toxicity Evaluation for Safety
Int. Conf. Machine Learning (ICML), Jul., 2025
Jeimin Jeon, Youngmin Oh, Junghyup Lee, Donghyeon Baek, Dohyung Kim, Chanho Eom, and Bumsub Ham
Subnet-Aware Dynamic Supernet Training for Neural Architecture Search
IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun., 2025
Youngmin Oh, Hyunju Lee, and Bumsub Ham
Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions
AAAI Conf. Artificial Intelligence (AAAI), Feb., 2025
Wonjun Lee, Bumsub Ham, and Suhyun Kim
Maximizing the Position Embedding for Vision Transformers with Global Average Pooling
AAAI Conf. Artificial Intelligence (AAAI), Feb., 2025
Byunggwan Son, Youngmin Oh, Donghyeon Baek, Bumsub Ham
FYI: Flip Your Images for Dataset Distillation
Eur. Conf. Comput. Vis. (ECCV), Oct., 2024
Dohyung Kim, Junghyup Lee, Jeimin Jeon, Jaehyeon Moon, and Bumsub Ham
Toward INT4 Fixed-Point Training via Exploring Quantization Error for Gradients
Eur. Conf. Comput. Vis. (ECCV), Oct., 2024
Junghyup Lee and Bumsub Ham
AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search
IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun., 2024
Jaehyeon Moon, Dohyung Kim, Junyong Cheon, and Bumsub Ham
Instance-Aware Quantization for Vision Transformers
IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun., 2024
Hyekang Park, Jongyoun Noh, Youngmin Oh, Donghyeon Baek, and Bumsub Ham
ACLS: Adaptive and Conditional Label Smoothing for Network Calibration
IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2023 (Oral presentation)
Jongyoun Noh, Hyekang Park, Junghyup Lee, and Bumsub Ham
RankMixup: Ranking-Based Mixup Training for Network Calibration
IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2023
Geon Lee, Sanghoon Lee, Dohyung Kim, Younhoon Shin, Yongsang Yoon, and Bumsub Ham
Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-identification
IEEE Int. Conf. Comput. Vis. (ICCV), Oct. 2023
Youngmin Oh, Donghyeon Baek, and Bumsub Ham
ALIFE: Adaptive Logit Regularizer and Feature Replay for Incremental Semantic Segmentation
Adv. Neural Inf. Process. Syst. (NeurIPS), Nov. 2022
Donghyeon Baek, Youngmin Oh, Sanghoon Lee, Junghyup Lee, and Bumsub Ham
Decomposed Knowledge Distillation for Class-incremental Semantic Segmentation
Adv. Neural Inf. Process. Syst. (NeurIPS), Nov. 2022
Geon Lee, Chanho Eom, Wonkyung Lee, Hyekang Park, and Bumsub Ham
Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation
Eur. Conf. Comput. Vis. (ECCV), Oct. 2022
Sanghoon Lee, Youngmin Oh, Donghyeon Baek, Junghyup Lee, and Bumsub Ham
OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search
Eur. Conf. Comput. Vis. (ECCV), Oct. 2022
Chanho Eom, Wonkyung Lee, Geon Lee and Bumsub Ham
Disentangled Representations for Short-Term and Long-Term Person Re-identification
IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI), 2022.
Junghyup Lee*, Dohyung Kim*, Wonkyung Lee, Jean Ponce, and Bumsub Ham (*equal contribution)
Learning Semantic Correspondence Exploiting an Object-level Prior
IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI), 2022.
Dohyung Kim, Junghyup Lee and Bumsub Ham
Distance-aware Quantization
IEEE Int. Conf. Comput. Vis. (ICCV), Oct., 2021
Donghyeon Baek*, Youngmin Oh*, and Bumsub Ham (*equal contribution)
Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation
IEEE Int. Conf. Comput. Vis. (ICCV), Oct., 2021
Chanho Eom, Geon Lee, Junghyup Lee and Bumsub Ham
Video-based Person Re-identification with Spatial and Temporal Memory Networks
IEEE Int. Conf. Comput. Vis. (ICCV), Oct., 2021
Hyunjong Park*, Sanghoon Lee*, Junghyup Lee and Bumsub Ham (*equal contribution)
Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences
IEEE Int. Conf. Comput. Vis. (ICCV), Oct., 2021
Youngmin Oh, Beomjun Kim, and Bumsub Ham
Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation
IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun., 2021
Junghyup Lee, Dohyung Kim, and Bumsub Ham
Network Quantization with Element-wise Gradient Scaling
IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun., 2021
Jongyoun Noh, Sanghoon Lee, and Bumsub Ham
HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection
IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun., 2021
Beomjun Kim, Jean Ponce, and Bumsub Ham
Deformable Kernel Networks for Joint Image Filtering
Int. J. Comput. Vis. (IJCV), 2021.
Learning with Privileged Information for Efficient Image Super-Resolution.
Wonkyung Lee*, Junghyup Lee*, Dohyung Kim* and Bumsub Ham (*equal contribution)
Eur. Conf. Comput. Vis. (ECCV), Aug., 2020.
Learning Memory-guided Normality for Anomaly Detection.
Hyunjong Park*, Jongyoon Noh* and Bumsub Ham (*equal contribution)
IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) Jun. 2020
Relation Network for Person Re-identification.
Hyunjong Park and Bumsub Ham
AAAI Conf. Artificial Intelligence (AAAI), Feb. 2020
Learning Disentangled Representation for Robust Person Re-identification
Chanho Eom and Bumsub Ham
Adv. Neural Inf. Process. Syst. (NeurIPS), Dec. 2019
SFNet: Learning Object-aware Semantic Correspondence.
Junghyup Lee*, Dohyung Kim*, and Bumsub Ham (*equal contribution)
IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2019 (Oral presentation)
