Scholar
Rui Men
Google Scholar ID: _0aiq2YAAAAJ
Qwen Team, Alibaba Group & Peking University
NLP
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
13,525
H-index
19
i10-index
20
Publications
20
Co-authors
9
list available
Publications
21 items
ID Balancing: Stable Training of Extremely Sparse MoE via PID-Based Load Control
2026
Cited
0
On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability
2026
Cited
0
Libra: Taming Attention Workload Skew in Long-Context LLM Training with Bounded Sequence Pool
2026
Cited
0
Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention
2026
Cited
0
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
2026
Cited
0
SAGE: Scalable Automated Robustness Augmentation for LLM Knowledge Evaluation
2026
Cited
0
Accelerating Compound LLM Training Workloads with Maestro
2026
Cited
0
SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training
2026
Cited
0
Load more
Co-authors
7 total
Junyang Lin
Qwen Team, Alibaba Group & Peking University
An Yang
Qwen Team, Peking University
Ge Li
Full Professor of Computer Science, Peking University
Zhi Jin, Fellow of IEEE and CCF
Professor - Peking University, Hongyi Visiting Professor - Wuhan University
Lili Mou
University of Alberta
Rui Yan (严睿)
Renmin University of China. Previously with Peking U. and UPenn
Xing Hu
Zhejiang University
