Wenjuan Han
Papers
2
Total Citations
6
H-Index
2
About
Wenjuan Han is a pioneering researcher at the forefront of multimodal artificial intelligence, with a specialized focus on integrating touch, language, and vision to advance robotic perception and human-computer interaction. Her major contributions center on addressing a critical gap in AI research: the underrepresentation of tactile data in multimodal systems. Through her landmark works, including the introduction of the Touch-Language-Vision Dataset and the large-scale Touch100k dataset, Han has established foundational resources that enable AI models to process and understand tactile information alongside visual and linguistic cues. These datasets, each garnering 3 citations in their early publication year of 2024, represent a significant step toward more comprehensive, human-like perception in robots. By systematically pairing tactile sensations with descriptive language and visual context, Han’s work empowers machines to grasp the nuanced interplay between physical texture, verbal description, and visual appearance. Her research promises to revolutionize fields from assistive robotics to virtual reality, where nuanced touch feedback is essential. As a rising voice in multimodal representation learning, Wenjuan Han is shaping a future where AI can truly feel, describe, and understand the physical world.
Research Focus
Key Achievements
Top Papers
- 1
- 2