Education
-
University of Illinois Urbana-Champaign
Bachelor of Science in Computer Science
Bachelor of Science in Liberal Arts & Sciences Major in Mathematics, Data Optimization Concentration
Bachelor of Science in Liberal Arts & Sciences Major in Statistics
GPA: 3.98
2023 - 2027
Papers
-
[2026] Revitalizing Local Democracy: A Human-Centered Audit of LLMs in City Council JournalismSubmitted to CHI 2026 HEAL Workshop
-
[2025] RSK linear operators and the Vershik-Kerov-Logan-Shepp curveSubmitted to Electronic Journal of Combinatorics
-
[2024] EveGuard: Defeating Vibration-based Side-Channel Eavesdropping with Audio Adversarial Perturbations
Research Experience
Carnegie Mellon University Human-Computer Interaction Institute (HCII)
Research Intern, May 2025 - present
- Designed and evaluated an automated journalism pipeline using SOTA LLMs to replicate end-to-end editorial workflows, from transcript segmentation to headline generation and topic prioritization.
- Orchestrated large-scale crowd-sourced study to establish human-evaluated ground truth validation.
- Demonstrated that LLM-based headline quality and topic prioritization can meet and exceed professional-standards.
- Presented research poster at the CMU HCII REU Symposium.
- Paper in submission to CHI 2026 Human-centered Evaluation and Auditing of Language Models (HEAL) workshop.
Illinois Mathematics Lab (formerly Illinois Geometry Lab)
Student Scholar, Jan 2024 - present
- Researched the data science perspective of sports matches at the Illinois Mathematics Lab.
- Built web scrapers with Selenium to scrape online data and analyzed the predictability of sports matches by comparing prediction accuracies of multiple sources including polls and the betting market.
- Evaluated efficiency of probabilistic predictions based on the betting market, Elo, and other mathematical models.
- Presented findings at Rose-Hulman Undergraduate Math Conference 2024, UIUC Undergraduate Research Symposium 2024, and Joint Mathematics Meeting 2025.
- Currently working on paper.
Illinois Combinatorics Lab for Undergraduates (ICLUE)
Research Mentee, Aug 2024 - May 2025
- Studying algebraic combinatorics, focusing on the Robinson-Schnested-Knuth correspondence.
- Used the Vershik-Kerov-Logan-Shepp curve to apply probability bounds on the RSK linear operator.
- Paper in submission to the Electronic Journal of Combinatorics.
National University of Singapore SEEDER Group
Research Intern, May 2024 - Aug 2024
- Developed machine learning pipeline to detect, classify, and analyze diseases found in plant leaves.
- Trained U-Net segmentation models and classification models based on convolutional neural networks to isolate and classify images using the TensorFlow framework, achieving 90% segmented classification rate.
- Generated synthetic images using custom trained cGAN model to increase data variety and volume.
- Stacked deep learning classification models with traditional machine learning models to achieve an increased detection accuracy of over 95%.
University of California San Diego
Research Intern, Jun 2020 - Aug 2023
- Developed EveGuard, a software-based defense framework to protect voice privacy from vibrometry-based side channels using adversarial audio by using a perturbation generator model (PGM) to effectively suppress sensor-based eavesdropping while preserving high audio quality.
- Implemented Eve-GAN, a novel domain translation task for inferring eavesdropped signals, enabling end-to-end training of PGM, utilizing few-shot learning techniques to reduce data collection overhead.
- Achieved a protection rate of over 97% against audio classifiers, hindering eavesdropped reconstruction.
- Paper published in the IEEE Symposium on Security and Privacy 2025.
Presentations
-
[2025] Carnegie Mellon University Human-Computer Interaction Institute REU Symposium
Title: LLMs for Extracting Agenda Items from City Council Meetings and Generating Newsworthy Headlines
Authors: David Xia
Program: CMU HCII REU
Presentation: Poster -
[2025] Algebra, Geometry and Combinatorics Day (joint work presented by Duy Phan)
Title: RSK linear operators and the Vershik-Kerov-Logan-Shepp curve
Authors: Duy Phan, David Xia
Program: Algecom
Presentation: Poster -
[2025] Joint Mathematics Meeting
Title: Predictability in Major Sports Leagues: Betting Market vs Model Based Predictions
Authors: David Xia
Program: Joint Mathematics Meeting
Presentation: Poster -
[2024] Rose-Hulman Undergraduate Math Conference
Title: Predictability in College Sports: Comparing the Accuracies of Prediction Models for College Football and Basketball Games
Authors: Yihan Gao, Samuel Lam, and David Xia
Program: Rose-Hulman Undergraduate Math Conference
Presentation: Oral Talk -
[2024] University of Illinois Urbana-Champaign Undergraduate Research Symposium
Title: Predictability and Competitiveness in Sports Leagues
Authors: Yihan Gao, Samuel Lam, and David Xia
Program: UIUC Undergraduate Research Symposium
Presentation: Poster
Service
[SP26] UIUC Algorithms and Models of Computation (CS 374) Course Assistant
Grants and Awards
[2025] CMU HCII REU: NSF 2349558
[2025] ICLUE RTG: NSF 1937241