Xilin Jiang 蔣晰林

I am a PhD candidate at Columbia University in Electrical Engineering and Zuckerman Mind Brain Behavior Institute. Advised by Prof. Nima Mesgarani in the Neural Acoustic Processing Lab, I study audio generative AI and multimodal LLMs, aim to model and to assist human Listening, Thinking, and Speaking, spanning Speech-to-Text (audio understanding, speech recognition), Text-to-Speech (speech synthesis), and Speech-to-Speech (dialog system, speech enhancement) applications.

I obtained my BS degree from UIUC ECE, where I worked with Dr. Efthymios Tzinis and Prof. Paris Smaragdis on speech separation. I will intern in Meta Superintelligence this summer.

[Our lab often has undergraduate/master’s research opportunities (Columbia students). Feel free to reach out.]

Education

• Columbia University, New York, NY

  PhD candidate after joint MS in Electrical Engineering

  Fall 2022 ~ Now💻☕, GPA: 4.12/4.00 (“A+”=4.33)

• University of Illinois Urbana–Champaign, IL

  BS in Computer Engineering, Highest Honor and Bronze Tablet 🏅🎓

  Fall 2018 ~ Fall 2021, GPA: 4.00/4.00

---

Internship

• Microsoft Research, Redmond, WA

  Summer 2025, Research Intern

  Mentors: Sebastian Braun & Hannes Gamper

  Project: Sci-Phi: A Large Language Model Spatial Audio Descriptor

• Amazon, Palo Alto, CA

  Summer 2021 & 2022, SDE Intern

---