Scholar
Zihan Qiu
Google Scholar ID: 24eVHiYAAAAJ
Qwen Team, Alibaba Group & IIIS, Tsinghua University
Mixture of Experts
Modular Deep Learning
Interpretability
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
3,614
H-index
9
i10-index
8
Publications
17
Co-authors
11
list available
Contact
No contact links provided.
Publications
11 items
Canzona: A Unified, Asynchronous, and Load-Balanced Framework for Distributed Matrix-based Optimizers
2026
Cited
0
A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training
2026
Cited
0
Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling
2025
Cited
0
A Controllable Examination for Long-Context Language Models
2025
Cited
0
Qwen3 Technical Report
2025
Cited
0
Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
2025
Cited
0
Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models
2025
Cited
0
Qwen2.5 Technical Report
2024
Cited
0
Load more
Resume (English only)
Co-authors
11 total
Zeyu Huang
The University of Edinburgh
Jie Fu
Shanghai AI Lab
Zili Wang
StepFun LLM Researcher & M-A-P
Ivan Titov
University of Edinburgh / University of Amsterdam
Jialong Wu
Ph.D. student, Tsinghua University
Jingren Zhou
Alibaba Group, Microsoft
Dayiheng Liu (刘大一恒)
Qwen Team, Alibaba Group
Junyang Lin
Qwen Team, Alibaba Group & Peking University
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up