Ti-Chung Cheng

Research Intern, Microsoft Research, Special Projects (Feb 2024 - May 2024) #

• Mentors: Madeleine Daepp, [Robert Ness](Robert Ness).
• Investigated empirically the impact of Large Language Models on high-stakes decision-making events through misinformation.
• Conducted time series, linguistic, and econometric analyses of 150K+ articles to substantiate claims about generative propaganda’s impact.
• Provided in-depth cultural and local insights, assuring accurate and nuanced discussion of regional issues in meetings and publications.

Research Intern, Software Analysis & Intelligence (SAINTES) Group, Microsoft Research (May 2023 - Aug 2023) #

• Mentors: Denae Ford Robinson, Nicole Forsgren, Carmen Badea, Christian Bird, Tom Zimmermann, Rob DeLine.
• Designed and built a prototype aimed to enhance software development operations (DevOps) and experiences using GitHub data.
• Constructed a complex Python-based LLM (Large-language Model)-powered team matching tool orchestrated using OpenAI API, Guidance, FLAML, and MySQL.
• Spearheaded metrics and proxies to understand and support team-matching decision processes.
• Outlined a two-stage within-subject qualitative study to explore expert users’ perceptions of LLM-based team matching processes.

Graduate Researcher, The University of Illinois at Urbana-Champaign (Aug 2018 - Present) #

• Led 3 human-computer interaction research projects in human-data interaction, individual preference elicitation, and smart home privacy.
• Designed, prototyped, and built an preference elicitation system using Quadratic Voting mechanisms with Nest.js, MongoDB, and Angular.
• Evaluated multiple interactive systems using interviews, surveys, questionnaires, and in-lab behavioral experiments.
• Analyzed experiment data using qualitative and quantitative methods, including open coding, thematic analysis, and bayesian analysis.
• Supported 2 human-computer interaction research projects in smart home user power dynamics and spreadsheet data analysis workflows.

Graduate Teaching Assistant, The University of Illinois at Urbana-Champaign (Aug 2018 - Present) #

• See Teaching for more details.

Software Engineer Intern, Salesforce (May 2020 - Aug 2020) #

• Developed VSCode Plugin for Salesforce developers to reduce XML development time by 2x using TypeScript.
• Contributed to Open Source RedHat XML VSCode extension (#292) and Salesforce VS Code extension (#2726)

Software Engineer Intern, Salesforce (May 2019 - Aug 2019) #

• Built pipelines and designed 3 dashboards for front-end cache monitoring using Java, Grafana, and Splunk to visualize daily logs on a billion scale.
• Optimized dashboard queries by 10x loc for better readability and maintainability.

Machine Learning Research Intern, KKBOX, Machine Learning Team (May 2018 - Aug 2018) #

• Mentor: Dr. Yian Chen
• Researched and implemented a natural language processing pipeline for mandarin name-entity recognition with 90%+ accuracy.
• Designed and built a pattern-based relation extraction pipeline for cross-language music content using 3B+ music data.

Undergraduate Research Assistant, The Chinese University of Hong Kong (Dec 2015 - Dec 2017) #

• Mentor: Prof. James Cheng
• Conducted research on distributed hash-based nearest-neighbor search algorithms with a publication at SIGMOD.
• Built a 15% more time-efficient and scalable Image Retrieval system compared to OpenCV FLANN Library.
• Implemented Collision Counting LSH in C++, details: Implementation and Analysis of Collision Counting LSH on Husky.

Web Administrator, RIH, The Chinese University of Hong Kong (2016 - 2017) #

Summer Research Intern, National Center for High-Performance Computing (July 2015 - Aug 2015) #

• Mentor: Dr.Ann, Hsing-Yen
• Designed and implemented MySQL database pipeline to retrieve and analyze malicious fast-flux domains.
• Intern report: Development of Bad Domain Tracking System
• Contributed to Tsai et al. Using BDTS to detect IP changes of malicious domains over time. TANET 2018.