Home
Publication
Projects
Board
Contact
Members
International Papers
Domestic Papers
Under Review
Gallery
Seminar
Conference Schedule
Course
Home
Members
Publication
International Papers
Domestic Papers
Under Review
Projects
Board
Gallery
Seminar
Conference Schedule
Course
Contact
Members
Professor
Publication
(* indicates first author, † indicates corresponding author)
Selected Publications
•
International Conferences
1.
Jouwon Song*, Sohyeon Kim*,
Kyeongbo Kong†,
“Uncertainty-Guided Graph Formulation via MWIS for Token Pruning in LVLMs”,
CVPR Findings
, 2026.
(Top-tier AI conference)
2.
Changwoo Baek*, Jouwon Song*, Sohyeon Kim*,
Kyeongbo Kong†,
“AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models”,
ICLR
, 2026.
(Top-tier AI conference, Acceptance Rate: 28%)
3.
In-Hwan Jin
*
, Hyeongju Mun
*
, Joonsoo Kim, Kugjin Yun,
Kyeongbo Kong
†
, “MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting
”,
ICLR
, 2026.
(Top-tier AI conference, Acceptance Rate: 28%)
4.
Inhwan Jin*, Haesoo Choo*, Seong-Hun Jeong, Heemoon Park, Junghwan Kim, Oh-joon Kwon,
Kyeongbo Kong†
, “Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape Images”,
ICLR
, 2025.
(Top-tier AI conference, Acceptance Rate: 32.08%)
5.
Junho Park*,
Kyeongbo Kong
*
,
Suk-Ju Kang
†
, “AttentionHand: Text-driven Controllable Hand Image Generation for 3D Hand Reconstruction in the Wild
”,
ECCV
, 2024. (Top-tier AI conference, Oral Presentation Acceptance Rate: 2.3%)
(Oral)
6.
Hyunwoo Yu
*
, Yubin Cho
*
, Beoungwoo Kang
*
, Moon Seunghun
*
,
Kyeongbo Kong
*
, Suk-Ju Kang†
, “Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentation
”,
ECCV
, 2024. (Top-tier AI conference, Acceptance Rate: 27.9%)
7.
ChangHee Yang*, Chan Hee Kang*
,
Kyeongbo Kong*
,
Hanni Oh,
Suk-Ju Kang
†
, “Person in Place: Generating Associative Skeleton-Guidance Maps for Human-Object Interaction Image Editing
”,
CVPR
, 2024.(Top-tier AI conference, Acceptance Rate: 23.6%)
8.
ChangHee Yang*,
Kyeongbo Kong*
, Sung-Jun Min*, Geonho Cha, Ho-Deok Jang, Dongyoon Wee, Suk-Ju Kang†, "SEFD: Learning to Distill Complex Pose and Occlusion",
ICCV
, 2023. (Top-tier AI conference, Acceptance Rate: 26.8%)
9.
Jae-hun Shim*, Hyunwoo Yu*,
Kyeongbo Kong*
, Suk-Ju Kang†, "FeedFormer: Revisiting Transformer Decoder for Efficient Semantic Segmentation",
AAAI
, 2023. (Top-tier AI conference, Acceptance Rate: 19.6%)
•
International Journals
1.
Changwoo Baek*, Jou Won Song,
Kyeongbo Kong† , “
Unsupervised Knowledge Distillation via Local Representations for Vision-Language Models”,
IEEE Signal Processing Letters
, 2025.
2.
Jihyun Kim
*
, Junho Park
*
,
Kyeongbo Kong
*
, Suk-Ju Kang†
, “Programmable-Room: Interactive Textured 3D Room Meshes Generation Empowered by Large Language Models
”,
IEEE Transactions on Multimedia
, 2025. (IF: 8.182)
3.
Min-jung Shin*, Woojune Park*, Minji Cho*,
Kyeongbo Kong*
, Hosung Son, Joonsoo Kim, Kugjin Yun, Gwangsoon Lee, Suk-Ju Kang†, "MosaicMVS: Mosaic-based Omnidirectional Multi-view Stereo for Indoor Scenes",
IEEE Transactions on Multimedia
, 2024. (IF: 8.182)
4.
Ginam Kim*, Hyunsung Kim*,
Kyeongbo Kong,
Jou Won Song, Suk-Ju Kang†, "Human Body-Aware Feature Extractor Using Attachable Feature Corrector for Human Pose Estimation",
IEEE Transactions on Multimedia
, 2023. (IF: 8.182)
5.
Sung-Jun Min*,
Kyeongbo Kong*
, Suk-Ju Kang†, "Out-of-Focus Image Deblurring for Mobile Display Vision Inspection",
IEEE Transactions on Circuits and Systems for Video Technology,
2023
.
(IF: 5.859)
6.
Kyeongbo Kong*
, Junggi Lee, Youngchul Kwak, Young-Rae Cho, Seong-Eun Kim, Woo-Jin Song†, "Penalty based Robust Learning with Noisy Labels",
Neurocomputing, 2022.
(IF: 5.719)
7.
Kyeongbo Kong*
, Woo-Jin Song, Moonsik Min†, "Knowledge Distillation-aided End-to-End Learning for Linear Precoding in Multiuser MIMO Downlink Systems with Finite-Rate Feedback",
IEEE Transactions on Vehicular Technology, 2021.
(IF: 5.978)
8.
Kyeongbo Kong*
, Seungjun Shin, Junggi Lee, Woo-Jin Song†, "How to Estimate Global Motion Non-Iteratively From a Coarsely Sampled Motion Vector Field",
IEEE Transactions on Circuits and Systems for Video Technology
, 2019. (IF: 4.133)
Kyeongbo Kong
Postdoctoral researcher
Publication
Submitted
[C1] Group-wise Layer Aggregation of Self-Supervised Representations for Speech Emotion Recognition
Sunchan Park*
, Hyung Soon Kim, Kyeongbo Kong†
International Journal Papers
[J2] Dimension-Specific Margins and Element-Wise Gradient Scaling for Enhanced Matryoshka Speaker Embedding
Sunchan Park*
, Hyung Soon Kim† IEEE Access, Mar. 2025. [J1] Reverberant environment embedding using dereverberation autoencoder
Sunchan Park*
, Hyung Soon Kim† Electronics Letters, Jan. 2025.
Sunchan Park
Ph.D Courses
JiAn Yang
Publication
Submitted
[J1] AttentionFlow: Text-to-Video Editing Using Motion Map Injection Module
Seong-Hun Jeong*
, Inhwan Jin*, Haesoo Choo*, Hyunjun Na*, Kyeongbo Kong†, (Submitted)
[J2] Embedding-Space Localization for Robust 3D TDOA Estimation
Seong-Hun Jeong*
, Hyeongju Mun, Dongho Kim, Youngik Choi, Kiin Kim, Hyosang Moon, Yonggi Hong and, Kyeongbo Kong†, (Submitted)
Seong-Hun Jeong
MS Courses
Publication
(* indicates first author, † indicates corresponding author)
International Conference Papers
[C4] Human Motion Aware Text-to-Video Generation with Explicit Camera Control
Taehoon Kim*, Chanhee Kang*, Jaehyuk Park*,
Daun Jeong*
, ChangHee Yang*, Suk-Ju Kang†
,
Kyeongbo Kong
†
WACV
,
Jan. 2024. (Second-tier AI conference)
Daun Jeong
Publication
(* indicates first author, † indicates corresponding author)
Submitted
[C1]
Anonymized Title
Hyeongju Mun*,
In-Hwan Jin*
, Sohyeong Kim, Kyeongbo Kong†
In-Hwan Jin
Publication
(* indicates first author, † indicates corresponding author)
Submitted
[0] An
noymous Submitted Paper
Changwoo Baek*,
Taehoon Kim*
, Woojin Lee*, Jungkwan Son, Seoyoung Lee, Jiyoung Kim, Kyeongbo Kong
†
Taehoon
Kim
Integrated BS-MS Courses
Project
•
홈로봇 환경을 고려한 야간 사람 인식 기술 개발 및 주간 얼굴 인식 성능 개선, LG Electronics, Korea /공동연구원 /23.12~24.12
•
홈로봇 환경을 고려한 VLM 기반시각 인식 기술 개발 및 상황 인지·추론 성능 개선, LG Electronics, Korea /공동연구원 / 25.5~
•
홈로봇 이상 상황 환경 감지 기술 개발, LG Electronics, Korea /공동연구원/ 25.7~
Changwoo Baek
Publication
(* indicates first author, † indicates corresponding author)
Submitted
1.
Hyeongju Mun
*,
In-Hwan Jin
*
, Sohyeong Kim, Kyeongbo Kong
†
, “Anonymized Title
”,
(Submitted)
HyeongJu Mun
Publication
(* indicates first author, † indicates corresponding author)
[J1] 동적 이미지 합성을 위한 4D Gaussian Splatting 기법 비교 및 연구 동향
우민수
*
,
진인환
*,
김준수, 윤국진, 공경보†
방송공학회논문지, 2025년 1월.
MinSoo Woo
Project
•
홈로봇 환경을 고려한 이상 상황·환경 감지 기술 개발, LG Electronics, Korea /공동연구원
Woojin Lee
Publication
(* indicates first author, † indicates corresponding author)
International Conference Papers
[C3] Uncertainty-Guided Graph Formulation via MWIS for Token Pruning in LVLMs
Jouwon Song*,
Sohyeon Kim*
, Kyeongbo Kong†
Sohyeon Kim
Publication
International Conference Papers
[C2] FluIDWorld: Fluid-like Interactive Dynamics for 4D Worlds
Hyeongju Mun*, In-Hwan Jin
*
,
Sohyeong Kim
, Kyeongbo Kong†
ICLRW
2026 (Top-tier AI conference workshop)
Sohyeong Kim
Publication
Jihoon Choi
Publication
Beomgwon Jo
Publication
Woo Hyeong Kim
Research Interns
Publication
(* indicates first author, † indicates corresponding author)
Submitted
[J1] Motion-to-Attention: Enhancing Attention Maps to Improve Performance of Text-Guided Video Editing Models
Seong-Hun Jeong*, Inhwan Jin*,
Haesoo Choo*
, Hyunjun Na*, Kyeongbo Kong
†
Haesoo Choo
Publication
JiWon Yun
Publication
Sang Yeon Yoon
Publication
Junsu Kim
