Junjie Chen

Peking University, China Academy of Launch Vehicle Technology

Papers

Total Citations

H-Index

About

Junjie Chen is a researcher working at the intersection of artificial intelligence, neuromorphic computing, and autonomous systems. His work spans two compelling frontiers: the development of biologically inspired neural architectures and the application of deep learning to real-world robotic systems. Chen's most recognized contribution lies in advancing the understanding of spiking neural networks (SNNs), a cutting-edge area of neuromorphic computing that seeks to replicate the energy efficiency and biological plausibility of the human brain. His 2025 survey on large-scale SNNs addresses critical progress and open challenges in the field, positioning him as a voice in the ongoing conversation about next-generation AI hardware and algorithms. Earlier work demonstrates his versatility, applying deep neural networks to situation assessment in soccer robotics — tackling practical challenges of scene understanding, data fusion, and high-level decision-making in dynamic environments. Though his citation profile is still developing, Chen's research touches on some of the most consequential questions in modern AI: how to build systems that are simultaneously intelligent, efficient, and grounded in biological reality. His trajectory suggests a researcher with broad technical range and an eye toward both theoretical rigor and applied impact.