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
Jia Hao — most-cited papers & profile · Multimodal
← authors
·
overview
Jia Hao
4
papers ·
0
citations
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
2025
Top co-authors
Bizhe Bai
· 1
Jialin Zheng
· 1
Peng Ye
· 1
Tao Chen
· 1
Xinyi Wang
· 1
Xudong Tan
· 1
Yaoxin Yang
· 1
Topics
Vision-Language Models
Video-Language
Embodied & Agents
Benchmarks