Scholar
Kangil Kim
Google Scholar ID: RZggOtkAAAAJ
Gwangju Institute of Science and Technology
Citations & Impact
Citations
604
H-index
10
i10-index
10
Publications
20
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- Accepted Neurips 2025 paper 'Preference Distillation via Value based Reinforcement Learning'.
- Published 'What and When to Look?: Temporal Span Proposal Network for Video Visual Relation Detection' in Expert Systems with Applications 2025.
- Accepted EMNLP 2025 'Probability Distribution Collapse: A Critical Bottleneck to Compact Unsupervised Neural Grammar Induction'.
- Presented 'RSCF: Relation-Semantics Consistent Filter for Entity Embedding of Knowledge Graph' at ACL 2025.
- Published 'CFASL: Composite Factor-Aligned Symmetry Learning for Disentanglement in Variational AutoEncoder' in TMLR 2024.
- And many other research achievements in top conferences and journals.
Research Experience
- Serves as the head of Intelligence Representation & Reasoning Lab at Gwangju Institute of Science and Technology (GIST).
Background
- Research interests include but are not limited to fundamental understanding and application of artificial intelligence; specialized in intelligent representation and reasoning.
Miscellany
- Welcomes strongly self-motivated students for Ph.D. and Postdoctoral programs, especially those who wish to dive into AI research for a deeper understanding.
