Huiqiang Jiang
Scholar

Huiqiang Jiang

Google Scholar ID: 99KtvpYAAAAJ
Microsoft Research Asia
Efficient AILLMsMLSys
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,586
 
H-index
15
 
i10-index
19
 
Publications
20
 
Co-authors
11
list available
Contact
GitHubOpen ↗
Publications
20 items
VecAttention: Vector-wise Sparse Attention for Accelerating Long Context Inference
2026
Cited
0
SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling
2026
Cited
0
ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs
2026
Cited
0
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
2025
Cited
0
MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training
2025
Cited
0
Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning
2025
Cited
0
Scaling LLM Test-Time Compute with Mobile NPU on Smartphones
2025
Cited
0
LeanK: Learnable K Cache Channel Pruning for Efficient Decoding
2025
Cited
0
Resume (English only)
Miscellany
  • Self-described as a 'fake MLSys/NLPer' and 'unpopular blogger'
  • Active on personal blog and Zhihu
  • Programming enthusiast, GitHub: @iofu728
  • Contact: iofu728@gmail.com, Phone: +86 178 xxxx xxxx
  • Actively seeking research interns interested in efficient LLM methods
Co-authors
11 total
Lili Qiu
Lili Qiu
NAI Fellow, ACM Fellow, IEEE Fellow, Professor, Dept. of Computer Science, The University of Texas
Yuqing Yang
Yuqing Yang
Microsoft
Qianhui Wu (武千惠)
Qianhui Wu (武千惠)
Microsoft Research
Chin-Yew Lin
Chin-Yew Lin
Principal Research Manager of Knowledge Computing Group, Microsoft Research Asia
Yucheng Li
Yucheng Li
University of Surrey
Zhenhua HAN
Zhenhua HAN
Microsoft Research Asia
Börje F. Karlsson
Börje F. Karlsson
Beijing Academy of Artificial Intelligence (BAAI)
Baotong Lu
Baotong Lu
Microsoft Research