Zeman Li
Scholar

Zeman Li

Google Scholar ID: 3cHbgQQAAAAJ
University of Southern California
Large Scale OptimizationMachine Learning
Citations & Impact
All-time
Citations
42
 
H-index
3
 
i10-index
1
 
Publications
5
 
Co-authors
11
list available
Resume (English only)
Academic Achievements
  • Paper 'PiKE: Adaptive Data Mixing for Multi-Task Learning Under Low Gradient Conflicts' accepted as Spotlight at NeurIPS 2026 (Top 688 out of 21,575 submissions)
  • Paper 'Synthetic Text Generation for Training Large Language Models via Gradient Matching' accepted at ICML 2025 (equal contribution)
  • Paper 'Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models' accepted at ICLR 2025
  • Paper 'Optimal Differentially Private Learning with Public Data' accepted at ICML 2024
  • Recipient of USC Viterbi School of Engineering Fellowship
  • Meritorious Winner (Top 697 out of 10,053 teams) in Mathematical Contest in Modeling (2021)
  • Finalist Award (Top 180 out of 13,753 teams) in Mathematical Contest in Modeling (2020)
  • Outstanding Winner of SIMIODE Challenge Using Differential Equations Modeling
  • Best Overall Project at Georgia Tech Capstone Design Expo