Curriculum Vitae
Profile
I am a PhD candidate in Electronic and Computer Engineering at The Hong Kong University of Science and Technology (HKUST) and the AI Chip Center for Emerging Smart Systems (ACCESS). My research focuses on AI accelerator architecture, digital compute-in-memory, ReRAM/SRAM hybrid architectures, compiler automation, edge RAG systems, quantization-aware efficient ML deployment, and LLM serving systems.
I am advised by Prof. Chi-Ying Tsui and Prof. Tim Kwang-Ting Cheng. I expect to graduate in Summer 2027 and am interested in postdoctoral opportunities related to AI hardware and efficient intelligence systems.
Education
The Hong Kong University of Science and Technology (HKUST)
PhD Candidate, Electronic and Computer Engineering
AI Chip Center for Emerging Smart Systems (ACCESS)
Aug. 2023 - expected Summer 2027
- Co-supervised by Prof. Chi-Ying Tsui and Prof. Tim Kwang-Ting Cheng
- GPA: 3.65/4.0
The Hong Kong University of Science and Technology (HKUST)
Visiting Research Intern, ACCESS
Nov. 2022 - Jul. 2023
- GPA: 4.0/4.3
University of Illinois Urbana-Champaign (UIUC)
Remote Exchange Student
Jul. 2021 - Aug. 2021
South China University of Technology (SCUT)
BEng, Microelectronics
Sep. 2019 - Jun. 2023
- Score: 93/100; GPA: 3.95/4.0
- Rank: 1/120
- IELTS: 7.0
- Co-supervised by Prof. Bin Li and Prof. Zhaohui Wu
Research Interests
- LLM serving systems: KV-cache management for concurrent agents and sparse attention
- Digital compute-in-memory circuits and architectures
- AI accelerators for DNNs, SNNs, Transformers, and edge LLM workloads
- ReRAM/SRAM hybrid in-memory computing and robust dataflow design
- Electronic design automation for CIM macro generation
- ML systems, edge RAG acceleration, quantization, and approximate computing
Selected Publications
For the full list, please see my publications page and Google Scholar profile.
EfficientAgent: What Makes KV Cache Offloading Work for Concurrent Agents? arXiv preprint, 2026. First author. arXiv / Code
PQ-HSA: Reusing Product-Quantized Scores for Hybrid Sparse-Approximate Attention arXiv preprint, 2026. First author. arXiv / Code
PQ-SIM A-SSCC, 2026. First author. CIM-based accelerator for approximate vector search in RAG.
SwiftCIM: a 55nm 23.2μJ/Token L-0.5 ReRAM Coupled Digital CIM Accelerator with Fully-Fused Multi-Head Attention Dataflow for FlashAttention ESSERC, 2026.
Balancing FP8 Computation Accuracy and Efficiency on Digital CIM via Shift-Aware On-the-fly Aligned-Mantissa Bitwidth Prediction IEEE TVLSI, 2026.
DS-CIM: Digital Stochastic Computing-In-Memory Featuring Accurate OR-Accumulation via Sample Region Remapping for Edge AI Models DATE, 2026.
DIRC-RAG: Accelerating Edge RAG with Robust High-Density and High-Loading-Bandwidth Digital In-ReRAM Computation ISLPED, 2025.
SynDCIM: A Performance-Aware Digital Computing-in-Memory Compiler with Multi-Spec-Oriented Subcircuit Synthesis DATE, 2025.
AutoDCIM: An Automated Digital CIM Compiler DAC, 2023.
Research Collaborations
I coordinate a multi-institution collaboration across HKUST, SCUT, Westlake University, SYSU, WHU, and other partners on in-memory computation, approximate computing, efficient algorithms, and emerging non-volatile memories. The projects below highlight first/co-first author and corresponding-author roles.
| Venue | Project | Leads |
|---|---|---|
| A-SSCC’26 | CIM-based approximate vector search for RAG | Kunming Shao (HKUST), Zhipeng Liao (Westlake) |
| ICCAD’26 | MoE compression and scheduling optimization | Jiangnan Yu, Kunming Shao (HKUST) |
| ICCAD’26 | Bit-block sparsity and quantization | Xu Chen (SCUT), Kunming Shao (HKUST) |
| ESSERC’26 | L-0.5 memory for multi-head attention | Kunming Shao, Xiaomeng Wang (HKUST) |
| IEEE TVLSI | FP8 computing on digital CIM | Liang Zhao (SCUT), Kunming Shao (HKUST) |
| DATE’26 | Digital stochastic CIM | Kunming Shao (HKUST), Liang Zhao (SCUT) |
| BioCAS’25 | Wearable edge devices | Zhipeng Liao (Westlake), Kunming Shao (HKUST) |
| ISLPED’25 | Edge LLM and RAG acceleration | Kunming Shao (HKUST), Zhipeng Liao (Westlake), Jiangnan Yu, Xiaomeng Wang (HKUST) |
| DAC’25 WIP | Approximate computing accelerator | Kunming Shao (HKUST), Liang Zhao (SCUT) |
| CICC’25 | Medical neural SoC | Fengshi Tian (HKUST), Jinbo Chen (Westlake), Kunming Shao (HKUST) |
| ISCAS’25 | Digital PE design | Liang Zhao (SCUT), Kunming Shao (HKUST) |
| DATE’25 | DCIM circuit design and automation | Kunming Shao, Fengshi Tian (HKUST) |
Honors and Awards
- HKUST RedBird Academic Excellence Award, 2026
- IEEE CASS Student Travel Grant, Jul. 2025
- HKUST Research Travel Grant, Mar. 2025
- SCUT Excellent Graduation Project (Dissertation), 2023, Top 1%
- Hong Kong PhD Fellowship, 2023, Top 3%
- HKUST RedBird PhD Recruitment Award, 2023
- Chinese National Scholarship, 2022, Top 2%
- Chinese National Scholarship, 2021, Top 2%
Selected Coursework
- ELEC6910A First Principles of Computer Vision, A+
- EESM5060 Embedded Systems, A+
- ELEC5160 Digital VLSI System Design and Design Automation, A+
Teaching
- ELEC3300 Introduction to Embedded Systems, Teaching Assistant
- ELEC4410 CMOS VLSI, Teaching Assistant
Service and Leadership
- Journal Reviewer, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD)
- Journal Reviewer, IEEE Transactions on Circuits and Systems II (TCAS-II)
- Vice President, Microelectronics Association, South China University of Technology
- Excellent Social Practice Volunteer, South China University of Technology