About

Biography

Hi! I’m Ge. I got my Ph.D. degree in Computer Science at University of California, Davis. I received my M.S. degree in computer science from the College of Information and Computer Sciences at University of Massachusetts, Amherst. I received my B.S. degree in Automation from the College of Control Science and Engineering at Zhejiang University.

Research

For my Ph.D., I’m doing research under the supervision of Prof. Davidson, Ian. I joined Machine Learning and Analytics Group led by Prof. Mahoney, Michael doing research in loss landscapes and its applications. I did research in the CV Lab working with Prof. Learned-Miller, Erik on my M.S. project (Video Stabilization via Super Congealing). I worked with Prof. Zhang, Yu on my B.S. project (SLAM: Simultaneous Localization and Mapping).

My research interests include: Machine Learning, Artificial Intelligence, Vision-Language Dual Models, and Large Language Models. My area of expertise is explainable AI and transparent models. Details about my research and projects can be found in the resume below.

Download the PDF version of

Resume

Researches

(Releasing Soon) From Categories to Spectrums: Improved PiliPrompt for Ordinal Classification.

(Releasing Soon) HALE: Hierarchical Aggregation of Local Linear Additive Explanations

(Releasing Soon) Visualizing Loss Functions as Topological Landscape Profiles

(Releasing Soon) LossLens: Diagnostics for Machine Learning Models through Loss Landscape Visual Analytics

PoliPrompt: A High-Performance Cost-Effective LLM-Based Text Classification Framework for Political Science

ChaosMining: A Benchmark to Evaluate Post-Hoc Local Attribution Methods in Low SNR Environments

SIG: Rethinking Baseline of Integrated Gradients from the Perspective of Shapley Value

Data augmentation with Mixup: Enhancing performance of a functional neuroimaging-based prognostic deep learning classifier in recent onset psychosis

Deep Learning for Prognosis Using Task-fMRI: A Novel Architecture and Training Scheme

Deep Learning in Neuroimaging: Overcoming Challenges With Emerging Approaches