Liu, Fangcheng
- Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity
2025/05/27 by Yehui Tang, Xiaosong Li, Tang, Yehui +41 · 22 voices · 4 citations
#cs.CL
- Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting
2024/04/29 by Liu, Fangcheng, Tang, Yehui, Liu, Zhenhua +3 · 9 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Unrestricted Adversarial Attacks on ImageNet Competition
2021/10/17 by Chen, Yuefeng, Mao, Xiaofeng, He, Yuan +34 · 5 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
- PanGu-π Pro:Rethinking Optimization and Architecture for Tiny Language Models
2024/02/05 by Yehui Tang, Tang, Yehui, Kai Han +17 · 4 citations
Computer Science · #Natural Language Processing Techniques #Speech and dialogue systems #Semantic Web and Ontologies
- PanGu-π: Enhancing Language Model Architectures via Nonlinearity Compensation
2023/12/27 by Yunhe Wang, Hanting Chen, Wang, Yunhe +36 · 2 citations
Computer Science · #Topic Modeling #Natural Language Processing Techniques #Speech Recognition and Synthesis
- Towards Transferable Unrestricted Adversarial Examples with Minimum Changes
2022/01/04 by Liu, Fangcheng, Zhang, Chao, Zhang, Hongyang · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
- Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs
2025/05/07 by Tang, Yehui, Yin, Yichun, Wang, Yaoyuan +71 · 3 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences