Qijun Luo
Scholar

Qijun Luo

Google Scholar ID: GMAEErsAAAAJ
Chinese University of Hong Kong, Shenzhen
Large language modelOptimization
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
62
 
H-index
4
 
i10-index
2
 
Publications
7
 
Co-authors
0
 
Contact
GitHubOpen ↗LinkedInOpen ↗
Publications
2 items
ARO: A New Lens On Matrix Optimization For Large Models
2026
Cited
0
StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs
2025
Cited
0
Resume
Academic Achievements
  • Paper 'StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs' accepted to NeurIPS 2025
  • Paper 'Accelerating Block Coordinate Descent for LLM Finetuning via Landscape Correction' accepted to NeurIPS 2025
  • Paper 'BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models' accepted to NeurIPS 2024
  • Paper 'Finite-Time Analysis of Fully Decentralized Single-Timescale Actor-Critic' published in TMLR 2023
  • NeurIPS Scholar Award (2024)
  • Top Reviewer @ NeurIPS (2024)
  • PhD Fellowship from Shenzhen Research Institute of Big Data (2022–2023)
  • Teaching Assistant Award, School of Data Science, CUHKSZ (2023)
  • Reviewer for ICLR (2024–2025), ICML (2025), NeurIPS (2024–2025), TMLR (2024–2025), SIMODS (2024)