Yueran (Hannah) Sun
M.S. Data Science · University of Washington

Hi👋 I’m Hannah.

I’m a Master’s student in Data Science at the University of Washington. My research explores how computing can help us better understand cultural heritage and make information more accessible through language.

Update: My co-authored paper, Beyond Readability Metrics: Plain Language Priorities in Disability Advocacy Organizations, has been accepted to ACM FAccT 2026!

Education

University of Washington · Seattle, WA
M.S. in Data Science · GPA 4.0/4.0 · Sept 2025 – Present (Expected Mar 2027)
Applied Statistics & Experimental Design · Software Design · Data Viz · Probability
University of Michigan · Ann Arbor, MI
B.S. Data Science (Minor: Mathematics) · GPA 3.71/4.0 · Aug 2021 – May 2025
NLP · ML · Data Mining · Databases · Web Systems · UI Development · Theory of Computation

Publications

Beyond Readability Metrics: Plain Language Priorities in Disability Advocacy Organizations
Accepted (ACM FAccT 2026)
Viral Images: Identifying Re-printings within 1.5 Million Photographs in Chronicling America
Submitted (ACM JOCCH Special Issue on Visual Heritage)

Research (overview)

UW · Lab for Computing Cultural Heritage
Graduate Student Researcher · Nov 2025 – Present
  • Analyzing clusters from 1.5M+ archival newspaper images to study visual reuse and circulation.
  • Built scalable lookup pipelines and concept labeling with CLIP embeddings.
UW · Language Accessibility Research Lab
Research Collaborator · Sep 2025 – Present
  • Developing segmentation + semantic alignment pipelines for original vs. plain-language text.
  • Evaluating alignment quality and linguistic changes with metrics + qualitative analysis.
MobiDrop (Zhejiang) Co., Ltd
Bioinformatics Research Assistant · Nov 2023 – May 2024
  • Pretrained scGPT on single-cell RNA-seq data; curated and processed large CELLxGENE samples.
  • Automated GPU training workflows with checkpointing and experiment tracking.

Industry Experience (overview)

Develop for Good · Product Manager, PainUSA
Oct 2025 – Feb 2026
  • Led a 5-person team to deliver a nonprofit website and interactive clinician lookup map.
  • Coordinated stakeholders, design handoff, and deployment documentation.
Ternary · Software Engineer Intern (Product Delivery)
Jun 2025 – Aug 2025
  • Integrated Prophet into a cloud cost forecasting API for daily/weekly predictions.
  • Improved reliability via CV, tuning, confidence intervals, and CI test coverage.
University of Michigan · MDP (ProQuest Team)
Jan 2024 – Dec 2024
  • Built an automated segmentation pipeline for historical newspaper front pages (images + OCR).
  • Validated pipeline variants and improved throughput and quality.
Pachira Information Technology (Hengqin) Co., Ltd
May 2024 – Aug 2024
  • Enhanced a RAG pipeline for an in-car Toyota voice assistant (accuracy, safety, interaction quality).
  • Implemented query handling components and deployed iterations for simulator testing.

Skills

Languages
PythonRSQLGo C/C++JavaScript/TypeScriptBash HTML/CSS
Tools & Platforms
GitLinuxDockerTerraform AWSGCPMongoDBIBM Db2 TableauJupyterCondaGitHub Actions
Frameworks & Libraries
PyTorchscikit-learnFastAPIReact LangChainNode.jsPandasNumPy DaskOpenCVXGBoostLightGBM

Contact

Email: yuerans@uw.edu