Ziyao Zeng
Papers
1
Total Citations
48
H-Index
1
About
Ziyao Zeng is a rising researcher at the forefront of embodied AI and multimodal machine learning, with a particular focus on bridging the gap between tactile sensing and other perceptual modalities. His most-cited work, "Binding Touch to Everything: Learning Unified Multimodal Tactile Representations" (2024, 48 citations), tackles the fundamental challenge of creating models that can learn cross-modal associations between touch and vision, audio, or text. This is a notoriously difficult problem due to the diversity of tactile sensors and the labor-intensive nature of collecting paired touch data. Zeng’s major contribution lies in developing representation learning techniques that unify tactile signals from different sensors into a shared embedding space, enabling robots to better understand object properties like texture, hardness, and temperature through touch. His work has significant implications for dexterous manipulation, human-robot interaction, and assistive technologies. Though early in his career, Zeng’s research is already garnering attention for its innovative approach to one of AI’s most underexplored senses, positioning him as a key voice in the push toward more physically grounded, multimodal AI systems.
Research Focus
Key Achievements
Top Papers
- 1