Liyuan Sun
Papers
1
Total Citations
2
H-Index
1
About
Liyuan Sun is a researcher whose work centers on advancing deep learning efficiency, with a particular focus on model compression and knowledge distillation. Their most-cited paper, "Feature fusion-based collaborative learning for knowledge distillation" (2021), introduces an innovative approach that enhances the performance of compact neural networks by enabling collaborative feature fusion between teacher and student models—a critical contribution for deploying deep networks in resource-constrained applications like autonomous driving and intelligent robotics. This work, which has garnered 2 citations, addresses the fundamental challenge of balancing model accuracy with computational efficiency. Sun’s research sits at the intersection of practical AI deployment and theoretical model optimization, offering solutions that make deep neural networks more accessible for real-world systems. Their contributions are particularly relevant for students and researchers exploring efficient AI architectures, as they provide a pathway to maintain high performance while reducing model size and inference costs. Through this focused work, Sun demonstrates a commitment to bridging the gap between cutting-edge deep learning research and its tangible applications in embedded and mobile environments.
Research Focus
Key Achievements
Top Papers
- 1Feature fusion-based collaborative learning for knowledge distillation2 citations · 2021