Scholar
Ligeng Zhu
Google Scholar ID: y0LVrtgAAAAJ
Nvidia
Citations & Impact
Citations
8,384
H-index
25
i10-index
27
Publications
20
Co-authors
23
list available
Publications
Resume (English only)
Academic Achievements
- - PockEngine: Sparse and Efficient Fine-tuning in a Pocket (MICRO-56, 2023)
- - On-Device Training Under 256KB Memory (NeurIPS, 2022)
- - Enable deep learning on mobile devices: Methods, systems, and applications (TODAES, 2022)
- - Delayed Gradient Averaging: Tolerate the Communication Latency for Federated Learning (NeurIPS, 2021)
- - IOS: Inter-Operator Scheduler for CNN Acceleration (MLSys, 2021)
- - TinyTL: Reduce Memory, Not Parameters for Efficient On-Device Learning (NeurIPS, 2020)
- - DataMix: Efficient Privacy-Preserving Edge-Cloud Inference (ECCV, 2020)
- - HAT: Hardware-Aware Transformers for Efficient Neural Machine Translation (ACL, 2020)
- - Distributed Training across the World (NeurIPS Workshop on Systems for ML, 2019)
- - Deep Leakage from Gradients (NeurIPS, 2019)
Research Experience
- - Conducting research on efficient designs for edge computing at MIT
Education
- - Ph.D. student at MIT, advisor: Prof. Song Han
- - Dual Degree Program between Zhejiang University and Simon Fraser University
Background
- - Research interests: efficient designs for edge computing
- - During undergraduate, worked with Prof. Brian Funt on colour vision and with Prof. Ping Tan on attribute recognition
Miscellany
- - Previously lived in Hangzhou and Vancouver
- - Open to potential collaborations
