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
Yunpu Ma — most-cited papers & profile · Multimodal
← authors
·
overview
Yunpu Ma
10
papers ·
0
citations ·
0
h-index
Munich Center for Quantum Science and Technology · Ludwig-Maximilians-Universität München
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention
2026
Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Models
2026
HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit
2026
UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking
2026
Top co-authors
Hao Wu
· 2
Junyan Lin
· 2
Yingqi Fan
· 2
Anhao Zhao
· 1
Hao Wu
· 1
Hao Wu
· 1
Jialiang Zhang
· 1
Jialiang Zhang
· 1
Jinyang Dai
· 1
Junlong Tong
· 1
Junlong Tong
· 1
Junlong Tong
· 1
Topics
Vision-Language Models
Video-Language
Visual QA & Reasoning
cs.CV
cs.CL
Benchmarks