Awesome Multimodal
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Miso Choi — most-cited papers & profile · Multimodal
← authors
·
overview
Miso Choi
4
papers ·
0
citations ·
2
h-index
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model Lineages
2026
SpatiO: Adaptive Test-Time Orchestration of Vision-Language Agents for Spatial Reasoning
2026
Focus, Don't Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding
2026
Top co-authors
Seonga Choi
· 2
Chan Yeong Hwang
· 1
Cheonyoung Park
· 1
Hyunyoung Lee
· 1
Jinkyu Kim
· 1
Jinkyu Kim
· 1
Jinkyu Kim
· 1
Jungbeom Lee
· 1
Jungbeom Lee
· 1
Kyeong-Jin Oh
· 1
Mincheol Kwon
· 1
Mincheol Kwon
· 1
Topics
Vision-Language Models
Instruction Tuning
Benchmarks
Visual QA & Reasoning
Video-Language
Embodied & Agents