Xiao Liang
Scholar

Xiao Liang

Google Scholar ID: JHWyBKIAAAAJ
University of California, Los Angeles
Large Language ModelsReinforcement Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
249
 
H-index
6
 
i10-index
4
 
Publications
19
 
Co-authors
8
list available
Contact
No contact links provided.
Publications
4 items
Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning
2026
Cited
0
Beyond Outliers: A Data-Free Layer-wise Mixed-Precision Quantization Approach Driven by Numerical and Structural Dual-Sensitivity
2026
Cited
0
Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability
2026
Cited
0
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
2026
Cited
4
Resume (English only)
Co-authors
8 total
Zhijiang Guo
Zhijiang Guo
HKUST (GZ) | HKUST
Yeyun Gong
Yeyun Gong
Microsoft Research Asia
Zhongzhi Li
Zhongzhi Li
Institute of Automation, Chinese Academy of Sciences
Weizhu Chen
Weizhu Chen
Microsoft, Technical Fellow
Yelong Shen
Yelong Shen
Microsoft
Ying Nian Wu
Ying Nian Wu
UCLA Department of Statistics and Data Science
Kai-Wei Chang
Kai-Wei Chang
Associate Professor, UCLA
Eric (Hanchen) Jiang
Eric (Hanchen) Jiang
University of California, Los Angeles