About
I am a Postdoctoral Fellow in the Department of Electrical and Computer Engineering at The University of Hong Kong, working with Prof. Han Wang. I received my Ph.D. from HKU in 2026, supervised by Prof. Han Wang and Prof. Zhongrui Wang, and my bachelor's degree from Huazhong University of Science and Technology in 2022.
I build compute-in-memory chips with memristors such as RRAM and carry them all the way to working systems: the chip, the test board and FPGA controller, and the algorithms that run on them. My research follows three directions. The first turns the physical properties of the device into computing resources and system elements. The second asks how to deploy and train neural networks efficiently on memristor-based analog compute-in-memory, through in-memory pruning, adaptive programming and fault-aware compensation. The third explores new computing paradigms built on memristors, such as fully analog, continuous-time neural ODE solvers for generative models.
I have authored 25 peer-reviewed papers (13 journal and 12 conference papers), including 6 as first or co-first author in Nature Communications, IEDM, DAC and ICCAD. As a co-author I have also published in Nature, Nature Machine Intelligence, Nature Nanotechnology, Nature Computational Science, Science Advances, Advanced Materials and IEEE Transactions on Computers.
News
Experience
Postdoctoral Fellow, Department of Electrical and Computer Engineering
Supervisor: Prof. Han Wang
Publications
Pruning random resistive memory for optimizing analog AI
Reconfigurable Digital RRAM Logic Enables In-situ Pruning and Learning for Edge AI
All-PWM RRAM Compute-in-Memory with In-Loop State Memory for Energy-Efficient Closed-Loop State Evolution
Two-dimensional materials for advanced back-end-of-line and wafer backside technologies
Efficient and accurate neural-field reconstruction using resistive memory
Resistive memory-based neural differential equation solver for score-based diffusion model
Adaptive Redox Resistive Memory Programming for Efficient and Robust Class-Incremental Learning
Comprehensive Reliability Enhancement for High-Precision RRAM Compute-in-Memory via Fault-Aware Hadamard Transform and Low-Rank Compensation
RRAM-DP: Device-Calibrated In-Memory Edge Learning
HFSCIM: Hybrid FeFET-SRAM CIM Architecture for Continuous-Time Inference and Online Reinforcement Learning
Reconfigurable 3D-VRRAM LUT-CiM with Greedy G-shuffle Quantization for End-to-End 4-bit ViTs in Edge Dense Prediction
AgeBalance: Low-Cost Lifetime Extension for SRAM-based PIM Accelerators
Parameter Efficient Machine Unlearning on Hybrid Resistive Memory based Compute-in-Memory Accelerators
A Monolithic Reconfigurable RRAM CIM Chip for Edge AI
Brain-Inspired In-Memory Data Pruning and Computing with TaOx Mem-Selectors
Resistive memory-based zero-shot liquid state machine for multimodal event data learning
Topology Optimization of Random Memristors for Input-Aware Dynamic SNN
Continuous-time digital twin with analog memristive neural ordinary differential equation solver
A Reliable, Reconfigurable 3T2R ReRAM-based Chip
Efficient Edge Vision Transformer Accelerator with Decoupled Chunk Attention and Hybrid Computing-In-Memory
Tunable Neuromorphic Computing for Dynamic Multi-Timescale Sensing in Motion Recognition
LSMR: Synergy Randomness in Liquid State Machine and RRAM-based Analog-digital Accelerator
SNNGX: Spiking Neural Networks on RRAM-based Neuromorphic Accelerator
Conditional Diffusion Model Acceleration with First-Demonstrated RRAM-Based In-Memory Neural Differential Equation Solver
Random memristor-based dynamic graph CNN for efficient point cloud learning at the edge
Echo State Graph Neural Networks with Analogue Random Resistive Memory Arrays
† equal contribution · * corresponding author
Service
Design, Automation and Test in Europe Conference (DATE 2027)
Track D8: Architectural and Microarchitectural Design · Dresden, Germany
Nature Communications
Science Advances
Talks
63rd Design Automation Conference (DAC), Long Beach, CA, USA
IEEE International Electron Devices Meeting (IEDM), San Francisco, CA, USA
Seminar, Department of ECE, The University of Hong Kong
62nd Design Automation Conference (DAC), San Francisco, CA, USA
Education
Ph.D., Electrical and Computer Engineering
Advisors: Prof. Han Wang and Prof. Zhongrui Wang
Graduate Academic International Program, Electrical and Computer Engineering
Exchange program, Electrical and Electronic Engineering
Bachelor's degree, School of Electronic Information and Communications
Teaching
The University of Hong Kong, Spring 2023, 2025 and 2026







