Zhihua Xiao
Ph.D. student in Electronic and Computer Engineering, HKUST
I’m a Ph.D. candidate in Electronics and Computer Engineering at The Hong Kong University of Science and Technology. Working in the Spintronic Qquantum Materials Laboritory (SQML), Under the supervision of Prof. Qiming SHAO. Meanwhile, I’m also working at AI Chip Center for Emerging Smart Systems (ACCESS). My research primarily focuses on the frontier of hardware-software co-design schemes for in-memory computing using emerging non-volatile technologies.
Current research interests
- Software-hardware codesign
Aimed to implement novel algorithms or accelerate existing algorithms using emerging devices. - Unified neuromorphic in-memory computing
Combining the advantages of artificial neural networks and spiking neural networks by designing unified neuromorphic in-memory computing hardware. - Computer architecture and device modeling
Benchmarking the performance of novel architectures and devices requires assistance from reliable modeling of the system and the devices.
For a deeper insight into my research, please refer to my Google Scholar.
If you wish to discuss with me, feel free to contact me via email.
selected publications
- Device Variation-Aware Adaptive Quantization for MRAM-based Accurate In-Memory Computing Without On-chip TrainingIn 2022 International Electron Devices Meeting (IEDM) , 2022
- Cryogenic in-memory computing using tunable chiral edge statesarXiv preprint arXiv:2209.09443, 2022
- Energy-efficient machine learning accelerator for binary neural networksIn Proceedings of the 2020 on Great Lakes Symposium on VLSI , 2020
- A multi-class objects detection coprocessor with dual feature space and weighted softmaxIEEE Transactions on Circuits and Systems II: Express Briefs, 2020