Publications
Selected Publications (Full List of Publications)
Stake the Points: Structure-Faithful Instance Unlearning
Kiseong Hong, JungKyoo Shin, and Eunwoo Kim
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2026.
Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models
Hyundong Jin, Dongyoon Han, and Eunwoo Kim
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2026.
Dual-Modality Anchor-Guided Filtering for Test-time Prompt Tuning
Jeongwon Choi and Eunwoo Kim
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (Findings), Jun. 2026.
XIL: Cross-Expanding Incremental Learning
Heayoun Choi, Hyundong Jin, and Eunwoo Kim
International Conference on Learning Representations (ICLR), Apr. 2026.
Dynamic Scale Position Embedding for Cross-Modal Representation Learning
Jungkyoo Shin, Sungmin Kang, Yoonsik Cho, and Eunwoo Kim
Neural Networks (NN), vol. 193, Jan. 2026.
Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models
Hyundong Jin, Hyung Jin Chang, and Eunwoo Kim
IEEE International Conference on Computer Vision (ICCV), Oct. 2025. [Project Page]
RainbowPrompt: Diversity-Enhanced Prompt-Evolving for Continual Learning
Kiseong Hong, Gyeong-Hyeon Kim, and Eunwoo Kim
IEEE International Conference on Computer Vision (ICCV), Oct. 2025. [Code]
Exploration and Exploitation in Continual Learning
Kiseong Hong, Hyundong Jin, Sungho Suh, and Eunwoo Kim
Neural Networks (NN), vol. 188, Aug. 2025.
Generative Modeling of Class Probability for Multi Modal Representation Learning
Jungkyoo Shin, Bumsoo Kim, and Eunwoo Kim
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2025.
(Highlight, Acceptance Rate: 3%)
Self-Corrective Task Planning by Inverse Prompting with Large Language Models
Jiho Lee, Hayun Lee, Jonghyeon Kim, Kyungjae Lee, and Eunwoo Kim
IEEE International Conference on Robotics and Automation (ICRA), May 2025. [Video]
Task Planning for Long-Horizon Cooking Tasks Based on Large Language Models
Jungkyoo Shin, Jieun Han, Seungjun Kim, Yoonseon Oh, and Eunwoo Kim
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct. 2024. [Video]
(Oral Presentation)
Mitigating Search Interference with Task-Aware Nested Search
Jiho Lee and Eunwoo Kim
IEEE Transactions on Image Processing (TIP), vol. 33, pp. 3102-3114, Apr. 2024.
Growing a Brain with Sparsity-Inducing Generation for Continual Learning
Hyundong Jin, Gyeong-Hyeon Kim, Chanho Ahn, and Eunwoo Kim
IEEE International Conference on Computer Vision (ICCV), Oct. 2023. [Project Page]
Helpful or Harmful: Inter-Task Association in Continual Learning
Hyundong Jin and Eunwoo Kim
European Conference on Computer Vision (ECCV), Oct. 2022. [Project Page]
Deep Elastic Networks with Model Selection for Multi-Task Learning
Chanho Ahn*, Eunwoo Kim*, and Songhwai Oh (* equal contribution)
IEEE International Conference on Computer Vision (ICCV), Oct. 2019.
Deep Virtual Networks for Memory Efficient Inference of Multiple Tasks
Eunwoo Kim, Chanho Ahn, Philip H.S. Torr, and Songhwai Oh
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2019.
NestedNet: Learning Nested Sparse Structures in Deep Neural Networks
Eunwoo Kim, Chanho Ahn, and Songhwai Oh
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2018.
(Spotlight Presentation)
Robust Elastic-Net Subspace Representation
Eunwoo Kim, Minsik Lee, and Songhwai Oh
IEEE Transactions on Image Processing (TIP), vol. 25, no. 9, pp. 4245-4259, Sep. 2016.
Elastic-Net Regularization of Singular Values for Robust Subspace Learning
Eunwoo Kim, Minsik Lee, and Songhwai Oh
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2015.
Structured Low-Rank Matrix Approximation in Gaussian Process Regression for Autonomous Robot Navigation
Eunwoo Kim, Sungjoon Choi, and Songhwai Oh
IEEE International Conference on Robotics and Automation (ICRA), May 2015. [Video]
Leveraged Non-Stationary Gaussian Process Regression for Autonomous Robot Navigation
Sungjoon Choi, Eunwoo Kim, and Songhwai Oh
IEEE International Conference on Robotics and Automation (ICRA), May 2015.
Efficient l1-Norm-Based Low-Rank Matrix Approximations for Large-Scale Problems Using Alternating Rectified Gradient Method
Eunwoo Kim, Minsik Lee, Chong-Ho Choi, Nojun Kwak, and Songhwai Oh
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), vol. 26, no. 2, pp. 237-251, Feb. 2015.
A Robust Autoregressive Gaussian Process Motion Model Using l1-Norm Based Low-Rank Kernel Matrix Approximation
Eunwoo Kim, Sungjoon Choi, and Songhwai Oh
IEEE International Conference on Intelligent Robots and Systems (IROS), Sep. 2014.
Real-Time Navigation in Crowded Dynamic Environments Using Gaussian Process Motion Control
Sungjoon Choi, Eunwoo Kim, and Songhwai Oh
IEEE International Conference on Robotics and Automation (ICRA), May 2014. [Video]