Tingle Li

Papers

Total Citations

H-Index

About

Tingle Li is a researcher at the forefront of multi-modal learning and computer vision, with a focus on bridging the gap between different data modalities to enhance machine perception. In their highly influential 2021 work, "Improving Multi-Modal Learning with Uni-Modal Teachers" (25 citations), Li introduced a novel framework that leverages uni-modal pre-trained models as "teachers" to guide multi-modal fusion, addressing a critical bottleneck in robotic and AI systems where joint training often leads to suboptimal representations. This contribution has been recognized for its practical impact on real-world applications, from autonomous systems to human-robot interaction. Additionally, Li has explored image super-resolution reconstruction through deep learning, as detailed in their 2021 study (6 citations), which surveys and advances techniques for reconstructing high-resolution images from low-resolution inputs—a key technology for medical imaging, surveillance, and multimedia. Li’s work is characterized by a deep understanding of both theoretical foundations and applied challenges, making their research a valuable resource for students and engineers seeking to push the boundaries of multi-modal learning and image enhancement.