Peter Chang
translateEN

Peter (Ting-Wei) Chang, MD

Two years of residency, three years of shipping LLM systems. Now at Academia Sinica, working on continual adaptation of large language models.

First author atCOLM 2026BMJ HCI 2025TREC 2024 · PLABA

Browse all 51 sites

  • Large language models
  • AI agents
  • Continual learning
  • Medical NLP
  • Clinical AI

About

Physician-turned-AI engineer with an M.D. and an M.S. in Computer Science (NLP Lab, National Taiwan University). Built an end-to-end AI platform (chatbot + CRM) at a Taipei AI startup, covering dataflow, inference, serving and monitoring. First author of publications at COLM 2026 and BMJ Health & Care Informatics.

My research sits at the intersection of large language models and clinical medicine: continual LLM adaptation (COLM 2026), medical imaging AI (BMJ Health & Care Informatics 2025), and plain-language adaptation of medical texts (TREC PLABA 2024).

Outside research I build some sites under peteraim.com covering conferences, medical AI, industry reports, startups and security See Projects. I also co-founded Beyond Medicine (醫外之境), a community empowering healthcare professionals to explore career paths beyond clinical practice.

Selected publications

All 7 publications →
COLM 2026First author

Smarter by the Moment: Environment-Driven Dynamic Policies for Continual LLM Improvement

Ting-Wei Chang, Po-Chun Chen, Hen-Hsen Huang, Hsin-Hsi Chen

TL;DRLets an LLM turn its own history into strategies — continual gains, no retraining.

Project pagearXivDOIPDFCode
BibTeX
@inproceedings{chang2026smarter,
  title     = {Smarter by the Moment: Environment-Driven Dynamic Policies for Continual {LLM} Improvement},
  author    = {Chang, Ting-Wei and Chen, Po-Chun and Huang, Hen-Hsen and Chen, Hsin-Hsi},
  booktitle = {Proceedings of the Conference on Language Modeling ({COLM})},
  year      = {2026},
  eprint    = {2609.16800},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  doi       = {10.48550/arXiv.2609.16800},
  url       = {https://arxiv.org/abs/2609.16800}
}
BMJ HCI 2025First author

Artificial intelligence for predicting interstitial fibrosis and tubular atrophy using diagnostic ultrasound imaging and biomarkers

Ting-Wei Chang, Chang-Yu Tsai, Zhen-Yi Tang, Cai-Mei Zheng, Chia-Te Liao, Chung-Yi Cheng, Mai-Szu Wu, Che-Chou Shen, Yen-Chung Lin

TL;DRPredicts kidney fibrosis from ultrasound and blood tests — no biopsy needed.

DOIPDF
BibTeX
@article{chang2025artificial,
  title   = {Artificial intelligence for predicting interstitial fibrosis and tubular atrophy using diagnostic ultrasound imaging and biomarkers},
  author  = {Chang, Ting-Wei and Tsai, Chang-Yu and Tang, Zhen-Yi and Zheng, Cai-Mei and Liao, Chia-Te and Cheng, Chung-Yi and Wu, Mai-Szu and Shen, Che-Chou and Lin, Yen-Chung},
  journal = {BMJ Health \& Care Informatics},
  volume  = {32},
  number  = {1},
  pages   = {e101192},
  year    = {2025},
  doi     = {10.1136/bmjhci-2024-101192}
}
TREC 2024 · PLABAFirst author

Enhancing Accessibility of Medical Texts through Large Language Model-Driven Plain Language Adaptation

Ting-Wei Chang, Hen-Hsen Huang, Hsin-Hsi Chen

TL;DRRewrites dense medical text into language patients can actually read.

arXivDOINIST SP 1329PDF
BibTeX
@inproceedings{chang2024enhancing,
  title     = {Enhancing Accessibility of Medical Texts through Large Language Model-Driven Plain Language Adaptation},
  author    = {Chang, Ting-Wei and Huang, Hen-Hsen and Chen, Hsin-Hsi},
  booktitle = {Proceedings of the Thirty-Third Text REtrieval Conference ({TREC} 2024)},
  series    = {NIST Special Publication 1329},
  year      = {2024},
  doi       = {10.6028/nist.sp.1329plaba-ntu_nlp},
  eprint    = {2609.17398},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url       = {https://arxiv.org/abs/2609.17398},
  note      = {PLABA track}
}

Selected projects

All 51 projects →

51 sites11 themes7 publications3 first-author

Experience

  1. Sep 2026 – Present

    Research Assistant

    Academia Sinica · Taipei

    Institute of Information Science

  2. Sep 2024 – Jul 2026

    Founding AI Engineer

    Genibuilder · Taipei

    Owned the AI platform (chatbot + CRM) from first feature to multi-tenant production serving 5+ businesses

    • Architected and built the platform on GCP, owning cloud architecture, deployment, and operations across dataflow, inference, serving, and monitoring
    • Redesigned the Genii-S agent architecture around parallel execution, cutting response latency by 90%
    • Powered the conversational AI behind a flagship client’s LINE community, supporting 400% follower growth
    • Built AI-driven functional and security review gates into the delivery pipeline. As ISO 27001 technical owner, defined AI and system security controls; the company passed its ISO/IEC 27001:2022 audit in Jul 2026
    • Extended the platform into higher education with Genii-Learning, piloted at NCCU with 100+ users; mentored an intern who built its student platform
  3. Jan 2025 – Present

    Co-Founder

    Beyond Medicine 醫外之境 · Taipei

    A community empowering healthcare professionals to explore diverse career paths and build futures beyond traditional medicine

  4. Jul 2024 – Aug 2024

    AI Project Engineer, Summer Intern

    Compal Electronics · Taipei

    Knowledge graphs, RAG, AI agents, agent memory, multi-agent systems

  5. Aug 2021 – Jul 2023

    Resident Physician, General Medicine

    Taipei Medical University Hospital · Taipei

    Two years of residency, with clinical AI research alongside

  6. Feb 2021 – Jul 2021

    3D Printing Teaching Assistant

    Taipei Medical University · Taipei

Education

  1. Sep 2023 – Jul 2025

    M.S. in Computer Science

    National Taiwan University, CSIE

    NLP Lab, advised by Prof. Hsin-Hsi Chen; the thesis became the COLM 2026 paper

  2. Sep 2014 – Jun 2020

    M.D. (Doctor of Medicine)

    Taipei Medical University, School of Medicine

    Licensed physician in Taiwan

Awards

  • 2024

    AOCR2024 AI Challenge

    Classification of acute appendicitis on contrast-enhanced CT; ranked 8/122 in the first stage and 11/25 in the second

  • 2022

    Letter of appreciation from the TMUH superintendent

    Produced 3D-printed organ models for donor body reconstruction after organ retrieval, across 10+ cases at TMUH, Wan Fang and Shuang Ho hospitals

  • 2021

    AI CUP 2021 Medical Dialog Analysis Competition

    Ranked 17/368

Talks & Workshops

  • 2026

    Online talk at 百業分享堂: “Turning long reports into interactive AI-built web pages: a medical-site case study”

    Live demo of turning the COMPUTEX 2026 site and the Stanford AI Index Report 2026 into shareable interactive pages with AI and no code, including how to vet a downloaded Skill and publish on GitHub; video published 6 Sep 2026

    Watch the talk
  • 2026

    Co-organizer and teaching assistant, Vibe Coding Basics workshop

    A volunteer team from the Evolving Intelligence (度化智能) learning community running hands-on AI workshops for non-technical people, open to everyone. First in-person session 22 Aug 2026 in Taipei, 4.58 / 5 overall satisfaction; own event documentation and the team’s knowledge base

    About the workshop
  • 2025

    Online talk at 百業分享堂: “From physician to AI: a career-transition journey”

    From observations inside the hospital and leaving the comfort zone to study AI, to advice for career changers; video published 27 Aug 2025

    Watch the talk
  • 2024

    Speaker, Google Developer Student Clubs @TMU

    9 May 2024; advances in NLP and how generative AI is reshaping the field

  • 2022

    Instructor, 3D printing workshops: medical humanities workshop and national workshop on 3D-printed organ models for organ donation

    26 Mar and 1 Oct 2022; taught 3D printing and guided about 50 participants through building organ models. The medical humanities workshop was hosted by TMU and Shuang Ho Hospital and covered by Da Ai TV news

    Watch the Da Ai TV report