Jianlong Zhou

Papers

Total Citations

H-Index

About

Jianlong Zhou is a researcher whose work bridges artificial intelligence, human-computer interaction, and explainable AI. His key contributions include advancing imitation learning—a paradigm that enables machines to replicate expert behaviors from demonstrations—with applications spanning autonomous driving, robotics, and video games. His highly cited 2021 survey on imitation learning, with 10 citations, systematically taxonomizes progress and challenges in the field, offering a foundational resource for researchers. Zhou also explores domain-adaptive stereo matching, as seen in his 2023 work on few-shot stereo matching using adaptive recursive networks (8 citations), which enhances AI's ability to generalize across diverse visual environments with limited data. His research is characterized by a focus on making AI systems more interpretable, adaptable, and capable of learning from human expertise—a critical step toward trustworthy and practical AI. Through these contributions, Zhou has shaped discussions on how machines can learn efficiently and transparently, earning recognition for his synthesis of complex topics and his impact on both theoretical frameworks and real-world applications.