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
Xiaoyi Yu — most-cited papers & profile · Multimodal
← authors
·
overview
Xiaoyi Yu
3
papers ·
0
citations ·
0
h-index
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression
2026
MSJoE: Jointly Evolving MLLM and Sampler for Efficient Long-Form Video Understanding
2026
Top co-authors
Guojie Zhu
· 1
Hao Jiang
· 1
Jian Luan
· 1
Jianzhong Ju
· 1
Jiaze Li
· 1
Kaisi Guan
· 1
Ruihua Song
· 1
Ruihua Song
· 1
Wenhui Tan
· 1
Wenhui Tan
· 1
Xiangyang Li
· 1
Xin Cheng
· 1
Topics
Video-Language
Benchmarks
Image-Text Retrieval
Audio-Visual
Visual QA & Reasoning