Scholar
Dongwon Kim
Google Scholar ID: abXotYsAAAAJ
POSTECH
Multi-modal learning
Representation learning
Computer vision
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
986
H-index
10
i10-index
10
Publications
12
Co-authors
15
list available
Contact
No contact links provided.
Publications
12 items
EventCoT: Event-centric Video Chain-of-thought for Reasoning Temporal Localization
2026
Cited
0
ACID: Action Consistency via Inverse Dynamics for Planning with World Models
2026
Cited
0
One-Step Generalization Ratio Guided Optimization for Domain Generalization
2026
Cited
0
Federated Learning for Feature Generalization with Convex Constraints
2026
Cited
0
Personalized Federated Learning for Gradient Alignment
2026
Cited
0
Structured State-Space Regularization for Compact and Generation-Friendly Image Tokenization
2026
Cited
0
Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model
2026
Cited
0
Automating High Energy Physics Data Analysis with LLM-Powered Agents
2025
Cited
0
Load more
Resume (English only)
Co-authors
15 total
Suha Kwak
POSTECH
Minsu Cho
Mu-Eun-Jae Endowed Chair Professor, Associate Professor of CSE & AI, POSTECH
Co-author 3
Sungyeon Kim
POSTECH
Cuiling Lan (兰翠玲)
Microsoft Research Asia
Wenjun (Kevin) Zeng, Ph.D., IEEE Fellow, Fellow of CAE
Vice President - Research, Eastern Institute of Technology, Ningbo
Chenglin Yang
Johns Hopkins University
Liang-Chieh Chen
Senior Principal Scientist, Amazon FAR, LA
