Wen-Chi (Vicky) Tsai

M.S. in Intelligent Information Systems · Language Technologies Institute, Carnegie Mellon University

I am a master's student in Intelligent Information Systems at Carnegie Mellon University's Language Technologies Institute, graduating December 2027, and a research assistant at NeuLab with Prof. Graham Neubig, working on agent harness and model co-optimization.

I build AI developer tools and workflow automation: test automation and LLM tooling at ASUS, geometric reasoning over AR room scans at RoomMuse, and edge LLM compression at NCU.

I am looking for Summer 2027 software engineering internships in developer tooling, infrastructure, and applied AI.

Off the clock: the gym, a table-tennis table, laps in the pool, K-pop on somewhere in the background, and a trip half-planned in another tab.

Experience & Projects Resume (PDF)
Wen-Chi (Vicky) Tsai
News
2026
Aug 10
Started my M.S. in Intelligent Information Systems at Carnegie Mellon University's Language Technologies Institute.
Aug 08
Wrapped up a summer at RoomMuse in Pittsburgh, shipping a geometric conflict engine and a classical-CV socket detector on top of RealityKit room scans.
Jun 08
Released an AI-workflow course for graduate school applications with AI POST, walking applicants through building their own research, drafting, and revision pipeline.
Jun 02
Joined RoomMuse as a startup engineer for the summer.
May 01
Our paper UAV Path Planning for Building Structure Inspection is published in the Ubi-Media 2026 proceedings (Springer CCIS vol. 2940).
Mar 31
Finished a 10-month software engineering internship at ASUS Open Cloud Infrastructure Software R&D, working on E2E test automation and LLM developer tooling.
Feb 28
Concluded my edge LLM compression work at NCU's Wireless Ad-Hoc and Sensor Networks Lab.
2025
Jun 23
Started as a software engineering intern at ASUS, on the Open Cloud Infrastructure Software R&D team.
Apr 25
Started writing the Vibe Coding column for AI POST, turning AI coding workflows into tutorials engineers can follow end to end.
2024
Nov 15
Won 3rd Place and the Highest Potential Award at the AIGO AI Challenge, hosted by Taiwan's Ministry of Digital Affairs, for our museum artifact recognition app.
2023
Apr 11
Joined the Wireless Ad-Hoc and Sensor Networks Lab at National Central University as an undergraduate research assistant.
Education
Carnegie Mellon University
Aug. 2026 - Dec. 2027
M.S. in Intelligent Information Systems
School of Computer Science, Language Technologies Institute
National Central University
Sep. 2022 - Jun. 2026
B.S., GPA 3.99 / 4.30
Computer Science and Information Engineering
Experience
Carnegie Mellon University
Sep. 2026 - Present
Research Assistant, NeuLab
Language Technologies Institute · advised by Prof. Graham Neubig and Lintang Sutawika
ASUS
Jun. 2025 - Mar. 2026
Software Engineering Intern
Open Cloud Infrastructure Software R&D
RoomMuse
Jun. 2026 - Aug. 2026
Startup Engineer
National Central University
Sep. 2025 - Feb. 2026
Research Assistant, Edge LLM Compression, advised by Min-Te Sun
Wireless Ad-Hoc and Sensor Networks Lab
AI POST
Apr. 2025 - Dec. 2025
AI Technical Writer and Educator
National Central University
Aug. 2024 - Jun. 2026
Frontend Engineer
College of Hakka Studies
Selected Publications (view all )
UAV Path Planning for Building Structure Inspection
UAV Path Planning for Building Structure Inspection

Wen-Chi Tsai, Yi-Peng Liu, Yu Wu, Yun-Sheng Chen, Chung-Lun Lai, Yu-Yu Chang, Min-Te Sun

Ubi-Media Computing, Pervasive Systems, Algorithms and Networks (Ubi-Media 2026) 2026 Communications in Computer and Information Science, vol. 2940, pp. 242-259

A dual-strategy planner for autonomous inspection of building structures: layered MST-DFS for traversing structured space, with collision-aware A* replanning when the structure blocks the tour. Evaluated in AirSim on real-world building models, generating paths over 5x faster with up to 14% shorter routes, both fully collision-free.

[Paper] [DOI]

UAV Path Planning for Building Structure Inspection

Wen-Chi Tsai, Yi-Peng Liu, Yu Wu, Yun-Sheng Chen, Chung-Lun Lai, Yu-Yu Chang, Min-Te Sun

Ubi-Media Computing, Pervasive Systems, Algorithms and Networks (Ubi-Media 2026) 2026 Communications in Computer and Information Science, vol. 2940, pp. 242-259

A dual-strategy planner for autonomous inspection of building structures: layered MST-DFS for traversing structured space, with collision-aware A* replanning when the structure blocks the tour. Evaluated in AirSim on real-world building models, generating paths over 5x faster with up to 14% shorter routes, both fully collision-free.

[Paper] [DOI]

All publications