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
Jun Song — most-cited papers & profile · Multimodal
← authors
·
overview
Jun Song
30
papers ·
20
citations ·
0
h-index
Alibaba Group (United States)
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games
2025 · 13 citations
GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagery
2026
Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding
2025
Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
2025
LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer
2024
Top co-authors
Bo Zheng
· 3
Yingyao Wang
· 3
Ziming Wang
· 2
Bo Du
· 1
Chi Chen
· 1
Di Wang
· 1
Fengxiang Wang
· 1
Hongda Sun
· 1
Honggang Chen
· 1
Jiahua Dong
· 1
Jiamang Wang
· 1
Jie Guo
· 1
Topics
Benchmarks
Vision-Language Models
Video-Language
Visual QA & Reasoning
Embodied & Agents