Haichuan Zhang

Work Experience

The Pennsylvania State University

Information Processing & Algorithms Laboratory

Position: Research Assistant
Developed the convergent network for image Inverse problem, with a focus on non-blind image deblurring.
Participated in the NTIRE challenges, contributing to tasks on Bokeh effect transformation and non-homogeneous dehazing.
Developed the algorithms for phase correction in ultrasound neuromodulation based on CT images, framing it as a model inversion problem.

NEC Laboratories America, Inc.

Information Processing & Algorithms Laboratory

Position: Research Internship
Developed a fiber sensor data restoration network based on a conditional diffusion model, which transforms low-quality fiber sensor data from cost-effective sensors into high-quality data.
Enabled downstream algorithms (such as fiber data classification models) trained or designed for high-quality data to accurately process low-quality fiber sensor data without requiring retraining or redesign.
Authored an internal report detailing the fiber sensor data restoration system.

Xi'an Jiaotong University

The Institute of Multimedia Knowledge Fusion and Engineering

Position: Science Software Engineer
Designed machine learning models for the diagnosis of Renal Cell Carcinoma (RCC).
Developed a cloud-based platform for AI-assisted pathological image annotation.
Conducted research on pathology information management and personalized diagnostics.

Xi'an Suoer Software Technology Co., Ltd.