PPaperPicks

Junmo Kim

Korea Advanced Institute of Science and Technology, KAIST, School of Electrical Engineering, Korea

25 papers at tracked venues · 15 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-7174-7932 ↗Google Scholar ↗Homepage ↗

Venues

NeurIPS ×4AAAI ×3CVPR ×3ECCV ×2EMNLP ×2ICCV ×2InterSpeech ×2MICCAI ×2WACV ×2ACL ×1ACM MM ×1ICML ×1

Frequent coauthors

Seunghee Koh
DBLP profile ↗ORCID search ↗
×3
Jongsuk Kim
DBLP profile ↗ORCID search ↗
×3
Minchan Kwon
DBLP profile ↗ORCID search ↗
×2
Chenshuang Zhang
DBLP profile ↗ORCID search ↗
×2
Changho Choi
DBLP profile ↗ORCID search ↗
×1
Haeil Lee
DBLP profile ↗ORCID search ↗
×1
Yooshin Cho
DBLP profile ↗ORCID search ↗
×1
Dongyeun Lee
DBLP profile ↗ORCID search ↗
×1
JooHyun Kwon
DBLP profile ↗ORCID search ↗
×1
Seoyeon Gye
DBLP profile ↗ORCID search ↗
×1
Chanho Lee
DBLP profile ↗ORCID search ↗
×1
Hyeong Gwon Hong
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Forget What Matters, Keep the Rest: Selective Unlearning of Informative Tokens
    ACL 2026 ·
    Seunghee Koh
    DBLP profile ↗ORCID search ↗
  2. B4DL: A Benchmark for 4D LiDAR LLM in Spatio-Temporal Understanding
    ACM MM 2025 ·
    Changho Choi
    DBLP profile ↗ORCID search ↗
  3. Beta Sampling is All You Need: Efficient Image Generation Strategy for Diffusion Models Using Stepwise Spectral Analysis
    WACV 2025 ·
    Haeil Lee
    DBLP profile ↗ORCID search ↗
  4. Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation
    ICCV 2025 ·
    Yooshin Cho
    DBLP profile ↗ORCID search ↗
  5. DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization
    ICCV 2025 ·
    Dongyeun Lee
    DBLP profile ↗ORCID search ↗
  6. Efficient Dynamic Scene Editing via 4D Gaussian-based Static-Dynamic Separation
    CVPR 2025 ·
    JooHyun Kwon
    DBLP profile ↗ORCID search ↗
  7. FairASR: Fair Audio Contrastive Learning for Automatic Speech Recognition
    InterSpeech 2025 ·
    Jongsuk Kim
    DBLP profile ↗ORCID search ↗
  8. PSGM-TR: A Transformer-Based Approach for Pulmonary Segment Segmentation Using Gaussian Mixture Models
    MICCAI 2025 ·
    Seunghee Koh
    DBLP profile ↗ORCID search ↗
  9. Preference Distillation via Value based Reinforcement Learning
    NeurIPS 2025 ·
    Minchan Kwon
    DBLP profile ↗ORCID search ↗
  10. Reducing the Content Bias for AI-generated Image Detection
    WACV 2025 ·
    Seoyeon Gye
    DBLP profile ↗ORCID search ↗
  11. Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision
    NeurIPS 2025 ·
    Chenshuang Zhang
    DBLP profile ↗ORCID search ↗
  12. AVCap: Leveraging Audio-Visual Features as Text Tokens for Captioning
    InterSpeech 2024 ·
    Jongsuk Kim
    DBLP profile ↗ORCID search ↗
  13. EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning
    ICML 2024 ·
    Jongsuk Kim
    DBLP profile ↗ORCID search ↗
  14. FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection
    AAAI 2024 ·
    Chanho Lee
    DBLP profile ↗ORCID search ↗
  15. Foreseeing Reconstruction Quality of Gradient Inversion: An Optimization Perspective
    AAAI 2024 ·
    Hyeong Gwon Hong
    DBLP profile ↗ORCID search ↗
  16. ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object
    CVPR 2024 ·
    Chenshuang Zhang
    DBLP profile ↗ORCID search ↗
  17. Implicit Steganography Beyond the Constraints of Modality
    ECCV 2024 ·
    Sojeong Song
    DBLP profile ↗ORCID search ↗
  18. Learning Neural Deformation Representation for 4D Dynamic Shape Generation
    ECCV 2024 ·
    Gyojin Han
    DBLP profile ↗ORCID search ↗
  19. Modeling Stereo-Confidence out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep
    AAAI 2024 ·
    Jae Young Lee
    DBLP profile ↗ORCID search ↗
  20. NICE: CVPR 2023 Challenge on Zero-shot Image Captioning
    CVPR 2024 ·
    Taehoon Kim
    DBLP profile ↗ORCID search ↗
  21. PSGMM: Pulmonary Segment Segmentation Based on Gaussian Mixture Model
    MICCAI 2024 ·
    Seunghee Koh
    DBLP profile ↗ORCID search ↗
  22. Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality
    EMNLP 2024 ·
    Youngtaek Oh
    DBLP profile ↗ORCID search ↗
  23. Self-supervised Transformation Learning for Equivariant Representations
    NeurIPS 2024 ·
    Jaemyung Yu
    DBLP profile ↗ORCID search ↗
  24. StablePrompt : Automatic Prompt Tuning using Reinforcement Learning for Large Language Model
    EMNLP 2024 ·
    Minchan Kwon
    DBLP profile ↗ORCID search ↗
  25. Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
    NeurIPS 2024 ·
    Jiwan Hur
    DBLP profile ↗ORCID search ↗