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
Xiaoyu Shen — most-cited papers & profile · Multimodal
← authors
·
overview
Xiaoyu Shen
9
papers ·
32
citations ·
24
h-index
Qinghai New Energy (China) · Qingdao Institute of Bioenergy and Bioprocess Technology · Eastern Institute of Technology, Ningbo
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking
2026
MCM-DPO: Multifaceted Cross-Modal Direct Preference Optimization for Alt-text Generation
2025
CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
2025
Top co-authors
Jinlan Fu
· 2
See-Kiong Ng
· 2
Shenzhen Huangfu
· 2
Xipeng Qiu
· 2
Bryan Hooi
· 1
Hao Fei
· 1
Hao Fei
· 1
Hao Wu
· 1
Jialiang Zhang
· 1
Junlong Tong
· 1
Junyan Lin
· 1
Xinghao Chen
· 1
Topics
Benchmarks
Visual QA & Reasoning
Vision-Language Models
Video-Language