Skip to content
View czhang657's full-sized avatar
1 follower · 1 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report czhang657

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
czhang657/README.md

Chengqian Zhang

Languages

Java Python C C++ SQL R HTML CSS JavaScript

Technologies

Docker PyTorch Linux

Full Stack Projects

  • My Website: Designed and developed the Yale International Alliance Summit website featuring event information and donation functionality using HTML, CSS, and JavaScript.
  • Summarizer: Implemented an application for summarizing academic papers by integrating a PDF loader and utilizing OpenAI's API and LangChain.

Machine Learning Projects

  • Research on Transferability of Data Cleaning Pipelines: As a Research Assistant at the D2I Lab, Georgia Institute of Technology, I led comprehensive experiments on the transferability of data cleaning pipelines, including standardization, handling missing values, and outlier detection across diverse categorical and time-series datasets. Leveraged dataset embeddings and the TaBERT model to analyze latent space representations, and evaluated the efficacy of data cleaning techniques for cross-domain transferability. Demonstrated that the MICE algorithm is particularly effective for time-series datasets with 0.15 and 0.10 drop probabilities. Established benchmarks for measuring transferability and clustering datasets, providing insights into the robustness of data cleaning techniques across different data scenarios.
  • Academic Name Disambiguation Pipeline: Developed an advanced academic name disambiguation pipeline using a pre-trained sentence transformer model and the WhoIsWho Toolkit. Addressed homonym and synonym issues in author attribution.
  • EvaDB Project: Implemented an application for summarizing academic papers using EvaDB, OpenAI's API, and LangChain.
  • IM4WAV: I Hear Your True Colors in Stereo: Developed an image-to-audio deep learning stereo-audio generation model based on IM2WAV, DinoV2, Clip, VQ-VAE, and sound localization techniques. Achieved a slight improvement over the current state-of-the-art IM2WAV model.

Skills

Technical: Docker, PyTorch, Linux
Programming Languages: Java, Python, C, C++, SQL, R, HTML, CSS

Education

Georgia Institute of Technology, College of Computing
Master of Science in Computer Science (Expected May 2025)

  • Concentration: Machine Learning
  • Core Courses: Computational Statistics, Deep Learning, Design & Analysis-Algorithms, Database System Implementation

Bachelor of Science in Computer Science (December 2023)

  • Concentration: Info/Artificial-Intelligence

Most Used Languages

Top Langs

Contact

Popular repositories Loading

  1. FaceRecognitionLogin FaceRecognitionLogin Public

    Face Recognition Login system which allows users to register and login with face ID.

    C++

  2. evaDB1 evaDB1 Public

    evaDB project 1 CS 4420

    Python

  3. czhang657 czhang657 Public