Senior Research Fellow, Director of AI Safety Research Center, Beijing-AISI
Ph.D., CAS Institute of Automation (with Prof. Yi Zeng)
B.Sc., School of Math & Stats, Xidian University
Research Focus: AI Safety & Alignment, Brain-Inspired Intelligence, Multimodal Learning
Reviewer for: IJCAI, ICML, NeurIPS, ICLR, TNNLS, TIP, TETCI
PandaGuard structures LLM safety evaluation as an interactive system with Attackers, Defenders, and Judges. It supports plug-and-play of various algorithms, backends, and interfaces.
STEP reproduces state-of-the-art Spiking Transformer models and offers a unified pipeline for classification, segmentation, and object detection. It enables fair, reproducible comparisons while remaining easy to extend.
BrainCog is an open source spiking neural network based brain-inspired cognitive intelligence engine for Brain-inspired AI, Embodied AI, and brain simulation.
