ML

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, project-driven exploration of foundational Artificial Intelligence algorithms. The coursework utilized the classic Pacman environment to bridge theoretical AI concepts with practical implementations, covering autonomous planning, decision-making under uncertainty, probabilistic tracking, and modern deep learning architectures. Core Project 1: State-Space Search & Adversarial Planning Engineered autonomous agents capable of navigating complex deterministic mazes and surviving stochastic, adversarial environments. Heuristic Search Strategies: Implemented uninformed search (DFS, BFS, UCS) and informed search (A* Search). Designed highly optimized, custom admissible and consistent heuristics to solve complex state-space problems, such as finding the optimal path to consume all food dots and navigating through specific corner coordinates. Adversarial Game Tree Search: Modeled adversarial ghost behaviors by developing multi-agent search algorithms. Implemented Minimax with Alpha-Beta Pruning to drastically reduce the expanded search space, and Expectimax to account for the stochastic, sub-optimal nature of random ghost movements. Designed custom evaluation functions to dynamically weigh game states. Core Project 2: Reinforcement Learning & MDPs Modeled the Pacman environment as a Markov Decision Process (MDP) to develop agents that learn optimal policies through trial and error. ...

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. ...