News

Article published in Cell Reports Physical Science
We introduce ENCODE, an implicit neural representation framework for scalable electron microscopy data compression that preserves high-fidelity structural details and supports temporal frame interpolation and denoising.

Two papers accepted on multiplicative noise removal (SIIMS and JMIV)
Two papers accepted by SIAM Journal on Imaging Sciences and Journal of …

Article published in npj Computational Materials
We introduce the Ptychographic Implicit Neural Representation …
Two articles published in IEEE ICASSP 2026
Our group presented two papers at ICASSP 2026 in Barcelona, Spain, covering topics in X-ray computed laminography and …
Article published in Patterns
We presents a data-driven solution for X-ray spectro-tomography that bypasses the need for manual markers or extensive …

Zipei and Qi receive Tutor Commendation Award 2024–25
Congratulations to Zipei Yan (顏子沛) and Qi Dai (代琦) on receiving the Tutor Commendation from the Department of Electronic Engineering, CUHK, for excellent teaching in 2024–2025.

Commentary published in Photon Science
We discuss the transformative potential of Agentic AI, an emerging paradigm that automates entire research workflows to revolutionize material characterization in synchrotron science.

Article published in IJCV
We propose a novel continuous low-rank factorization (CLoRF) by integrating two neural representations into the matrix factorization, capturing spatial and spectral information, respectively.

Article published in ACS Nano
By employing super-resolved nanoscale X-ray computed tomography (Nano-CT), scanning probe nanodiffraction imaging (SPNDI), and advanced data-driven statistical analysis, we unveil the ubiquitous …

Article published in Cell
We describe two complementary TEMPO (transmembrane electrical measurements performed optically) voltage-sensing technologies that capture neural oscillations up to 100 Hz. Fiber-optic TEMPO achieves …

Article published in IEEE TBME
We propose a Lorentzian-model Informed Neural Representation (LINR) framework for high-quality CEST mapping. LINR employs a self-supervised neural architecture embedding the Lorentzian equation, the …

Article published in Advanced Materials
This study analyzes the failure of commercial wireless earbud batteries as a model system within their intended usage context.

Article published in EES Batteries
This study utilizes explainable machine learning (ML) methodologies to tackle this challenge by analyzing a comprehensive database derived from published differential scanning calorimeter (DSC) …

Article published in Appl. Phys. Lett.
We utilize fused secondary and backscattered electron images to reconstruct 3D microstructures of porous cathodes with high fidelity.

Jizhou elevated to IEEE Senior Member
Jizhou Li was elected as the Senior Member of IEEE. Senior Member is the highest grade for which IEEE members can apply.

Article published in Chin. Phys. Lett.
With physics-informed representation learning, we introduce a data compression method tailored for battery X-ray tomography.