Research Project
Single-Pass Document Scanning for Question Answering
Training state space models for long-context question answering that scan documents once and answer efficiently.
Artificial intelligence · NLP · Learning tools
Researching efficient language models and tools for learning with data.
I am a fourth-year undergraduate at UC San Diego, double majoring in Data Science at the Halıcıoğlu Data Science Institute and Cognitive Science with a specialization in Machine Learning and Neural Computation.
Research
Current Projects
My work focuses on artificial intelligence research, especially machine learning algorithms, large language models, and computational approaches to natural language.
Research Project
How Novices Use Program Visualizations to Understand Code that Manipulates Data Tables
A computing education study of how novice programmers use visualizations to reason about data-table code.
Publications
Single-Pass Document Scanning for Question Answering
arXiv Preprint, 2025
TL;DR: We trained State Space Models (Mamba-2) for long-context Q&A, achieving performance comparable to GPT-4o on extremely long documents while being more computationally efficient.
@inproceedings{cao2025singlepassdocumentscanning, title={Single-Pass Document Scanning for Question Answering}, author={Cao, Weili and Wang, Jianyou and Zheng, Youze and Bao, Longtian and Zheng, Qirui and Berg-Kirkpatrick, Taylor and Paturi, Ramamohan and Bergen, Leon}, booktitle={Proceedings of the 2025 Conference on Language Modeling (COLM)}, year={2025}, }How Novices Use Program Visualizations to Understand Code that Manipulates Data Tables
Proceedings of the 56th ACM Technical Symposium on Computer Science Education V. 1 (SIGCSE TS 25), ACM, 2025
TL;DR: A case study on how novices use program visualizations to understand code manipulating data tables, revealing the importance of visualizations in learning programming.
@inproceedings{wu2025novices, title={How Novices Use Program Visualizations to Understand Code that Manipulates Data Tables}, author={Wu, Ylesia and Zheng, Qirui and Lau, Sam}, booktitle={Proceedings of the 56th ACM Technical Symposium on Computer Science Education V. 1}, pages={1267--1273}, year={2025} }UC San Diego
- Teaching Assistant (Spring, Summer, Fall 2024) DSC 80: Practice and Application of Data Science
- Teaching Assistant (Summer 2025) DSC 20 Programming and Basic Data Structures for Data Science
News
- July 7th, 2025: Conference paper Single-Pass Document Scanning for Question Answering. accepted at COLM 2025. Will attend the conference in October 2025.
- October 1st, 2024: Conference paper How Novices Use Program Visualizations to Understand Code that Manipulates Data Tables. accepted at SIGCSE 2025. Attended the conference in March 2025.
- June 2024: Joined the Laboratory for Emerging Intelligence as a research assistant.
- March 2024 - August 2024: Joined the The Data Science Teaching and Learning Lab as a research assistant.
- August 2022: Started undergrad studies at UC San Diego.