Yunfan Jiang

Papers

Total Citations

H-Index

About

Yunfan Jiang is a rising star in robotics and artificial intelligence, whose research centers on general-purpose robot manipulation, multimodal learning, and prompt-based control systems. His most influential contribution is the VIMA framework, introduced in his highly cited 2022 paper "VIMA: General Robot Manipulation with Multimodal Prompts" (65 citations). This work pioneered the application of prompt-based learning—a paradigm that revolutionized natural language processing—to robotics, enabling a single robot model to interpret and execute diverse tasks specified through multimodal inputs, including images, text, and one-shot demonstrations. By bridging the gap between language model flexibility and physical robot control, Jiang has opened new pathways for creating more adaptable and intuitive robotic systems. His research demonstrates how robots can generalize across tasks without task-specific retraining, a critical step toward embodied AI. With his innovative synthesis of NLP-inspired architectures and real-world manipulation, Jiang is shaping the future of human-robot interaction, making complex robotic systems more accessible and versatile for both researchers and practitioners.