Jiangtao Feng

Papers

Total Citations

H-Index

About

Dr. Jiangtao Feng is a leading researcher in cross-lingual and multimodal AI, with a focus on vision-language navigation (VLN) and grounded language understanding. His pioneering work challenges the English-centric bias in robotics and human-robot interaction, most notably through his landmark 2019 paper "Cross-Lingual Vision-Language Navigation," which introduced frameworks for commanding robots using natural language instructions beyond English. This contribution has been instrumental in expanding VLN systems to serve diverse linguistic communities, bridging critical gaps in accessibility and real-world deployment. Dr. Feng’s research integrates natural language processing, computer vision, and robotics, advancing how machines interpret and act upon multilingual, spatially grounded commands. With over 2 citations on this foundational work alone, his influence is steadily growing among researchers in embodied AI and cross-lingual transfer learning. Dr. Feng’s achievements underscore a commitment to inclusive, globally applicable AI systems—making his profile essential reading for students and researchers interested in the future of language-driven robotics and multilingual human-machine collaboration.