Huan Ling

Papers

Total Citations

H-Index

About

Huan Ling’s research lies at the intersection of computer vision, human-robot interaction, and natural language processing, with a focus on enabling machines to learn from non-expert human guidance. In their most cited work, “Teaching Machines to Describe Images with Natural Language Feedback” (2017, 38 citations), Ling pioneered a framework that brings a human teacher into the learning loop, allowing robots to improve their image description abilities through iterative, natural language corrections rather than relying solely on pre-labeled datasets. This approach—extended in a closely related 2017 paper (32 citations)—demonstrates how descriptive feedback can refine a model’s understanding of visual scenes, making AI more accessible and adaptable for real-world household applications. By shifting from static training to interactive, language-driven learning, Ling’s contributions address a critical gap in robotics: how to empower everyday users to guide intelligent systems. Their work has been influential in advancing human-in-the-loop machine learning, with combined citations approaching 70, and stands as a key step toward robots that can learn naturally from the people they serve.