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
Sunghwan Hong — most-cited papers & profile · Multimodal
← authors
·
overview
Sunghwan Hong
15
papers ·
29
citations ·
0
h-index
Samsung (South Korea) · Samsung (United States)
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation
2023 · 4 citations
Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models
2026
Seg4diff: Unveiling Open-vocabulary Segmentation In Text-to-image Diffusion Transformers
2025
Visual Representation Alignment For Multimodal Large Language Models
2025
Top co-authors
Seungryong Kim
· 4
Heeseong Shin
· 3
Anurag Arnab
· 2
Heeji Yoon
· 2
Jaewoo Jung
· 2
Paul Hongsuck Seo
· 2
Chanho Eom
· 1
Donghyun Kim
· 1
Honggyu An
· 1
Jisang Han
· 1
Marcel Gr\"opl
· 1
Marc Pollefeys
· 1
Topics
Vision-Language Models
Visual QA & Reasoning
Image-Text Retrieval
Video-Language
Benchmarks
Instruction Tuning
Audio-Visual