Scholar
Jihyung Kil
Google Scholar ID: C3O0uxcAAAAJ
Adobe Research
GUI/Computer-Using Agent
AI Agent
Embodied Agent
Vision and Language
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
593
H-index
9
i10-index
8
Publications
12
Co-authors
10
list available
Contact
Email
jkil@adobe.com
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
12 items
Agentic Context Learning with Self-Discovered Specification
2026
Cited
0
Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations
2026
Cited
0
DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning
2026
Cited
0
Anticipatory Planning for Multimodal AI Agents
2026
Cited
0
MiLDEdit: Reasoning-Based Multi-Layer Design Document Editing
arXiv.org · 2026
Cited
0
Text-Conditioned Background Generation for Editable Multi-Layer Documents
2025
Cited
0
GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding
2025
Cited
0
MLLM as a UI Judge: Benchmarking Multimodal LLMs for Predicting Human Perception of User Interfaces
2025
Cited
0
Load more
Resume (English only)
Co-authors
10 total
Wei-Lun (Harry) Chao 趙偉崙
Associate Professor, The Ohio State University
Yu Su
Distinguished Associate Professor of Computer Science, Ohio State University
Chan Hee (Luke) Song
PhD Candiate, The Ohio State University
Tai-Yu (Daniel) Pan
Google
Co-author 5
Soravit "Beer" Changpinyo
Google DeepMind
Xi Chen
Google DeepMind
Radu Soricut
Distinguished Scientist at Google
