ShanghaiTech

4D Holographic Particle Tracking Velocimetry (PTV) (Feb 2026 - Present) Undergraduate Researcher | Computational Imaging Lab, UC Berkeley Advised by Dr. Nalini Singh & Mingxuan Cai Details Lagrangian Representation: Departed from traditional grid-based views by adopting a Lagrangian perspective, using precise floating-point coordinates to represent individual particles for off-grid trajectory tracking. Forward Modeling: Developed an analytical forward projection model to optimize optical kernels, improving the fidelity of in-line holographic reconstructions. Hybrid Initialization: Implemented an Angular Spectrum Method (ASM) combined with Gaussian representations for robust particle localization. Physics-Informed Neural Field: Represented complex velocity fields using Multi-Layer Perceptrons (MLPs) to regularize ill-posed inverse problems in fluid dynamics. Pipeline Engineering: Built an end-to-end pipeline integrating particle localization and 4D flow field reconstruction. Zero-Day Vulnerability Detection via Revelio (Mar 2026 - Present) Research Assistant | Sky Computing Lab, UC Berkeley Advised by Yiwei Hou ...

Course Overview An intensive, transistor-level design project focused on creating a complete EEG signal processing module supporting end-to-end EEG acquisition and conversion. The architecture encompasses a preamplifier, a sampling module, a single-slope analog-to-digital converter (ADC), and a digital-to-analog converter (DAC). Core Project: End-to-End EEG Signal Processing Module Designed and simulated a comprehensive integrated circuit module from the ground up, focusing on the precise amplification and digital conversion of weak biological electrical signals. ...

Course Overview An intensive exploration of deep learning applications in medical imaging. The coursework involved implementing and optimizing advanced neural network architectures for dynamic MRI reconstruction and cardiac image segmentation, balancing computational efficiency with high-fidelity clinical outputs. Core Project 1: Dynamic MRI Reconstruction Engineered a deep learning pipeline for reconstructing dynamic cardiac cine MRI from 5x undersampled k-space data, addressing the trade-off between spatial-temporal resolution and acquisition time. ...

Course Overview A practical exploration of Object-Oriented Programming (OOP) and software design principles through the end-to-end development of a fully functional 2D Roguelike game. The project utilized Python to build custom game mechanics, focusing on event-driven state management, rendering pipelines, and collision physics. Core Project: Python-Based Roguelike RPG Co-developed an expansive, tile-based 2D RPG featuring dynamic map environments, scalable enemy logic, and encapsulated rendering systems. 1. Game Engine & Rendering Subsystems Architected a centralized GameManager infrastructure to orchestrate global event loops, entity updates, and frame-by-frame rendering. ...