Kai-Wei Chang is a Postdoctoral Fellow at MIT CSAIL (2025 ~ 2027 expected), working in the Spoken Language System Group led by Dr. James Glass.

He holds a Ph.D. from National Taiwan University, where he was advised by Prof. Hung-yi Lee. He graduated in 2025, with a dissertation titled "Towards a Universal Speech Model: Prompting Speech Language Models for Diverse Speech Processing Tasks" (Best Dissertation Award, ACLCLP 2025).

He has served as a tutorial speaker at ICASSP 2023 and ICASSP 2024, organized the Codec SUPERB Challenge at SLT 2024, and served as Session Chair at ICASSP 2025. He is also a Meta-reviewer for ASRU 2025 and ICASSP 2026, the Program Chair and Publication Chair for ROCLING 2025, and the Publication Chair for ISCSLP 2026.

🔥 In May 2025, Kai-Wei Chang started TaigiTube 台語水管, a website that helps people learn Taiwanese in a lively, everyday context with clips from Taiwanese dramas. Within three days, it attracted attention from major Taiwanese broadcasters including FTV, PTS, and TVBS, and led to a 40-minute interview on BCC radio.

Selected Publications

• Game-Time: Evaluating Temporal Dynamics in Spoken Language Models
  Kai-Wei Chang^*, En-Pei Hu^*, Chun-Yi Kuan, Wenze Ren, Wei-Chih Chen, Guan-Ting Lin, Yu Tsao, Shao-Hua Sun, Hung-Yi Lee, James Glass
  ICASSP 2026

• On The Landscape of Spoken Language Models: A Comprehensive Survey
  Kai-Wei Chang^*, Siddhant Arora^*, Chung-Ming Chien^*, Yifan Peng^*, Haibin Wu^*, Yossi Adi^†, Emmanuel Dupoux^†, Hung-Yi Lee^†, Karen Livescu^†, Shinji Watanabe^†
  TMLR 2025

• SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks
  Kai-Wei Chang, Haibin Wu, Yu-Kai Wang, Yuan-Kuei Wu, Hua Shen, Wei-Cheng Tseng, Iu-thing Kang, Shang-Wen Li, Hung-yi Lee
  IEEE/ACM TASLP Volume 32, 2024

For the full publication list, please refer to my google scholar

Internship

• Meta Codec Avatars Lab at Reality Labs Research - Research Scientist Intern
  Pittsburgh, June 2023 - Dec. 2023

Industrial Cooperation

• Meta - Data Mining with Seamless Communication Feb. 2022 - 2024

• ASUS - Taiwanese Speech Recognition & Translation Nov. 2021 - 2025

• Bonio Inc. - Taiwanese Pronounciation Evaluation System Oct. 2021 - June 2022

Conference Tutorials

• ICASSP 2024: Parameter-Efficient and Prompt Learning for Speech and Language Foundation Models
  Chao-Han Huck Yang (Amazon), Pin-Yu Chen (IBM Research), Hung-yi Lee (National Taiwan University),Kai-Wei Chang (National Taiwan University), Cheng-Han Chiang (National Taiwan University)

• ICASSP 2023: Parameter‑Efficient Learning for Speech and Language Processing: Adapters, Prompts, and Reprogramming
  Pin-Yu Chen (IBM Research), Hung-yi Lee (National Taiwan University), Chao-Han Huck Yang (Georgia Institute of Technology), Kai-Wei Chang (National Taiwan University), Cheng-Han Chiang (National Taiwan University)

Teaching Assistant & Leadership

• Machine Learning, 2021 Spring - Head Teaching Assistant Instrutor: Prof. Hung-yi Lee

  Led and coordinated with over 40 teaching assistants and over 1300 students.

• Linear Algebra, 2020 Fall - Head Teaching Assistant Instrutor: Prof. Hung-yi Lee

  Led and coordinated with over 6 teaching assistants and about 130 students.