Changxin Tian
Scholar

Changxin Tian

Google Scholar ID: QrStHzUAAAAJ
Renmin University of China & Ant Group
Large Language Models
Google Scholar↗
Citations & Impact
All-time
Citations
1,704
 
H-index
9
 
i10-index
9
 
Publications
16
 
Co-authors
4
list available
Contact
No contact links provided.
Publications
8 items
Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design
2026
Cited
0
MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging
2026
Cited
0
Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation
2025
Cited
0
MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics
2025
Cited
0
Arrows of Math Reasoning Data Synthesis for Large Language Models: Diversity, Complexity and Correctness
2025
Cited
0
Towards Greater Leverage: Scaling Laws for Efficient Mixture-of-Experts Language Models
2025
Cited
0
WSM: Decay-Free Learning Rate Schedule via Checkpoint Merging for LLM Pre-training
2025
Cited
0
Toward Stable and Consistent Evaluation Results: A New Methodology for Base Model Evaluation
2025
Cited
0
Resume (English only)
Co-authors
4 total
Wayne Xin Zhao
Wayne Xin Zhao
Professor, Renmin University of China
Ji-Rong Wen
Ji-Rong Wen
Gaoling School of Artificial Intelligence, Renmin University of China
Jun Zhou
Jun Zhou
Ant Group, Alibaba Group, Zhejiang University
Zhiqiang Zhang
Zhiqiang Zhang
Ant Group