Duidi Wu
Papers
2
Total Citations
30
H-Index
2
About
Duidi Wu is a pioneering researcher at the intersection of human-robot collaboration, multimodal language models, and spatial intelligence. Their work focuses on bridging the gap between natural human communication and robotic perception, enabling more intuitive and adaptive interactions in shared environments. Wu’s major contributions include developing frameworks that empower robots to understand human intentions through vision-language models, even in few-shot learning scenarios—a critical advancement for real-world collaboration where labeled data is scarce. Their 2025 paper, "Empowering natural human–robot collaboration through multimodal language models and spatial intelligence," has already garnered 16 citations, highlighting its influence in shaping next-generation human-robot systems. Another key work, "H2R Bridge: Transferring vision-language models to few-shot intention meta-perception in human robot collaboration," with 14 citations, introduces a novel bridge architecture that significantly improves robots’ ability to infer human goals from minimal examples. Wu’s research is notable for its practical pathways toward seamless human-robot teamwork, with implications for manufacturing, healthcare, and assistive robotics. Their achievements underscore a commitment to advancing spatial reasoning and language-driven robot cognition, positioning them as a rising leader in the field.
Research Focus
Key Achievements
Top Papers
- 1
- 2