default author photo

Yong Liu

Renmin University of China

SCHOLARLY PAPERS

3

DOWNLOADS

216

TOTAL CITATIONS

2

Scholarly Papers (3)

Actions:
Email selected abstracts
1.

Distilling Mathematical Reasoning Capabilities into Small Language Models

Number of pages: 27 Posted: 03 Apr 2024
xunyu zhu, Jian Li, Yong Liu, Can Ma and Weiping Wang
Chinese Academy of Sciences, Chinese Academy of Sciences, Renmin University of China, affiliation not provided to SSRN and Chinese Academy of Sciences
Downloads 105 (664,543)
Citation 2

Abstract:

Loading...

Large Language Models, Knowledge Distillation, Mathematical Reasoning, Chain-of-Thought, Program-of-Thought

2.

Communication-Efficient Personalized Federal Graph Learning Via Low-Rank Decomposition

Downloads 66 (907,769)

Communication-Efficient Personalized Federal Graph Learning Via Low-Rank Decomposition

Number of pages: 19 Posted: 10 Dec 2024 Last Revised: 15 Jan 2025
Ruyue Liu, Rong Yin, Xiangzhen Bo, Xiaoshuai Hao, Xingrui Zhou, Yong Liu, Can Ma and Weiping Wang
affiliation not provided to SSRN, affiliation not provided to SSRN, Wuhan University of Technology, Xiaomi EV, China, Xidian University, Renmin University of China, affiliation not provided to SSRN and Chinese Academy of Sciences
Downloads 46 (1,131,842)

Abstract:

Loading...

Federated Graph Learning, Low-Rank Decomposition, Non-IID, Distributed Learning

Communication-Efficient Personalized Federal Graph Learning Via Low-Rank Decomposition

Number of pages: 25 Posted: 03 Jul 2025
Ruyue Liu, Rong Yin, Xiangzhen Bo, Xiaoshuai Hao, Xingrui Zhou, Yong Liu, Liang Li, Jinwen Zhong, Can Ma and Weiping Wang
affiliation not provided to SSRN, affiliation not provided to SSRN, Wuhan University of Technology, Xiaomi EV, China, Xidian University, Renmin University of China, affiliation not provided to SSRN, affiliation not provided to SSRN, affiliation not provided to SSRN and Chinese Academy of Sciences
Downloads 20 (1,500,232)

Abstract:

Loading...

Federated Graph Learning, Low-Rank Decomposition, Non-IID

3.

Improving Differentiable Architecture Search Via Self-Distillation

Number of pages: 27 Posted: 28 Feb 2023
xunyu zhu, Jian Li, Yong Liu and Weiping Wang
Chinese Academy of Sciences, Chinese Academy of Sciences, Renmin University of China and Chinese Academy of Sciences
Downloads 45 (1,121,190)

Abstract:

Loading...

neural architecture search, Neural networks, smoothness, knowledge distillation, sharpness-aware minimization