Spike-based architectures
Designing Spiking Neural Networks and Spiking Transformers that make meaningful use of neural dynamics and sparse computation.
TEFormer →I am a Ph.D. student at the Institute of Automation, Chinese Academy of Sciences and the University of Chinese Academy of Sciences, affiliated with Beijing Zhongguancun Academy. Before starting my Ph.D. in 2024, I received my B.Eng. in Internet of Things from Beijing University of Posts and Telecommunications.
My main research interest is brain-inspired learning, particularly how neural dynamics and spike-based representations can support efficient computation over time. My work on Spiking Transformers spans temporal interaction, architecture design, and reproducible evaluation. Looking ahead, I am interested in extending these ideas toward brain-inspired foundation architectures and brain–computer interfaces, including neural decoding.
My broader research experience also includes LLM jailbreak evaluation, lightweight safety alignment, and trustworthy vision–language–action systems. These works are included alongside my brain-inspired research below.