8000 DungMinhDao (Minh-Dung Dao) · GitHub
[go: up one dir, main page]

Skip to content
View DungMinhDao's full-sized avatar
🎯
Focusing
🎯
Focusing

Highlights

  • Pro

Block or report DungMinhDao

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
DungMinhDao/README.md

Minh-Dung Dao

PhD researcher in Computer Science at University College Cork, in the Reliable AI Lab (RAIL), funded by the Research Ireland Centre for Research Training in AI (CRT-AI).

I build AI that clinicians and educators can trust. Working with UCC's ASSERT clinical simulation centre and the National Learning Analytics Unit, I'm developing an AI assessment system for simulation-based clinical training. It scores performance from multi-camera video, thermal imaging, audio and speech, ties every score to time-stamped evidence, and defers to the educator when that evidence isn't strong enough. I also work on LLM agents and multi-agent systems.

Website | Google Scholar | LinkedIn | ORCID

Research interests

  • Reliable multimodal AI: evidence-grounded, calibrated assessment
  • AI for clinical education and patient safety
  • LLM agents, agentic design patterns and multi-agent collaboration

Publications

I publish as Minh-Dung Dao. Earlier papers list me as Dung Dao.

  • Agentic Design Patterns: A System-Theoretic Framework
    Minh-Dung Dao*, Q. M. Le*, H. T. Lam, D.-T. Le, Q.-V. Pham, B. O'Sullivan, H. D. Nguyen
    NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models (LAW) | arXiv
  • AI-Empowered Handover Tool Design in Medical Practice Towards Patient Safety
    K. Salim, Minh-Dung Dao, H. D. Nguyen
    HCI International 2026 (SCSM), Springer LNCS | DOI
  • Multi-Agent Collaboration Mechanisms: A Survey of LLMs
    K.-T. Tran, Dung Dao, M.-D. Nguyen, Q.-V. Pham, B. O'Sullivan, H. D. Nguyen
    arXiv, 2025 | arXiv
  • LLM-Powered Multimodal AI Conversations for Diabetes Prevention
    Dung Dao, J. Y. C. Teo, W. Wang, H. D. Nguyen
    AIQAM '24 Workshop at ACM ICMR 2024 | DOI
  • VinaLLaMA: LLaMA-based Vietnamese Foundation Model
    Q. Nguyen, H. Pham, Dung Dao
    arXiv, 2023 | arXiv

* Equal contribution. Full list on Google Scholar.

Before the PhD

  • FPT Software AI Center, AI Resident (2 years): fine-tuned and deployed LLMs for domain-specific chatbots; built time-series models for industry clients
  • Vingroup Big Data Institute: speech classification models for the ViVi voice assistant in VinFast cars
  • WorldQuant University, MSc in Financial Engineering: capstone on deep learning for currency pair trading

Service and awards

  • Session chair, "Agentic AI and Data Analytics", HCI International 2026
  • Reviewer for NeurIPS, ECAI, ICDM, AICS and MMM
  • Irish Collegiate Programming Contest: Third Prize (2025), 4th place (2024)
  • Vice President, Vietnamese Students' Association in Ireland (SVIE)

Most of my PhD work uses clinical recordings that can't be shared, so the day-to-day code lives in private repositories.

Pinned Loading

  1. LocalOCR LocalOCR Public

    Local OCR and Markdown workbench for Apple Silicon: compare 14 OCR engines side by side (Apple Vision, Tesseract, MLX vision-language models, marker), get lean Markdown for LLMs, and turn Markdown …

    Python

  2. pair-trading-currency-deep-learning pair-trading-currency-deep-learning Public

    MScFE capstone (WorldQuant University): deep learning vs classical models for EUR/USD synthetic-spread pair trading, with walk-forward backtesting

    Jupyter Notebook 1

  3. AttritionRiskAssessment AttritionRiskAssessment Public

    A dynamic risk assessment system for client attrition: auto retrain and redeploy (MLOps)

    Python 2

  4. DS_AI_Python_Exercises DS_AI_Python_Exercises Public

    Repository of Python homework exercises created by me for the course IT1010E - Introduction to Programming

    Jupyter Notebook 2

  5. MFEA_python MFEA_python Public

    This is a re-implementation of the original MATLAB/Octave MFEA code

    Python 1

0