Jinan Xu

Beijing Jiaotong University

Papers

3

Total Citations

21

H-Index

3

About

Jinan Xu is a leading researcher in multimodal artificial intelligence, with a core focus on integrating touch, language, and vision to create more holistic machine perception systems. Her major contribution lies in pioneering the intersection of tactile sensing with natural language processing—a domain that had been largely overlooked in favor of visual-tactile research. Xu spearheaded the creation of **Touch100k**, the first large-scale, paired touch-language-vision dataset, which provides a critical foundation for training AI models to understand and describe physical interactions through text. This work, detailed in her 2025 paper that has already garnered **15 citations**, addresses a fundamental gap in robotics and human-computer interaction: enabling machines to not only feel but also articulate tactile experiences. Her 2024 publications further established the theoretical framework for this multimodal paradigm, demonstrating how language can serve as a bridge between raw tactile data and semantic understanding. By advancing touch-centric multimodal representation, Xu is laying the groundwork for more intuitive robots, enhanced virtual reality, and richer assistive technologies, making her a pivotal figure in the next wave of embodied AI research.

Research Focus

Key Achievements

3
H-Index
3
Papers
21
Total Citations
7
Avg Citations/Paper
🏆 Most Cited Paper
Touch100k: A large-scale touch-language-vision dataset for touch-centric multimodal representation
15 citations · 2025
📈 Most Prolific Year: 2024 (2 Papers)
🤝 Key Collaborators: 12
🏛 Institutions: Beijing Jiaotong University

Top Papers

  1. 1
  2. 2
  3. 3

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 4 days ago