Guoxun Zhang

NeuroPilot converts heterogeneous intravital neural recordings into stable population activity maps, enabling behavioral decoding and structured neural dynamics analysis across behavioral states.

The paper integrates CAD blueprints with diffusion models to explicitly program protein shapes, demonstrating emergent functions through molecular design.

The paper introduces DeepWonder3D, a pipeline for rapid and robust 3D neuronal extraction from multi-view projections, achieving high fidelity and efficiency in calcium dynamics analysis.

This paper introduces a method to remove defocus backgrounds in fluorescence microscopy using dark channels and dual frequency separation, significantly improving image quality.

AGP-Net predicts spatial gene expression from histopathology images by leveraging textual gene descriptions to generalize across unseen genes and datasets.

This paper introduces DeepCAD, a self-supervised learning method to enhance calcium imaging by reducing noise and improving SNR, leading to better neuron extraction and spike inference.

This paper introduces an unsupervised image transformation method for optical microscopy that avoids data annotation and achieves high-fidelity image transformations across modalities.