Minh-Dung Dao

PhD researcher at University College Cork

I build AI that clinicians and educators can trust.

Portrait of Minh-Dung Dao

I’m a PhD researcher in the Reliable AI Lab at University College Cork, supervised by Assoc. Prof. Hoang D. (Harry) Nguyen and funded by the Research Ireland Centre for Research Training in AI (CRT-AI). 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, grounds every score in time-stamped evidence, and defers to the educator when that evidence is insufficient.

I also work on LLM agents and multi-agent systems. Before the PhD I spent two years as an AI Resident at FPT Software AI Center, and I hold an MSc in Financial Engineering from WorldQuant University.

I finish my PhD in 2027 and am open to research and applied-science roles from then. I publish as Minh-Dung Dao (earlier papers: Dung Dao), and you may also know me as Robert.

News

  1. Joined the Network of Vietnamese Experts in Ireland, launched by the Embassy of Vietnam to connect Vietnamese expertise in Ireland.

  2. Chaired the session “Agentic AI and Data Analytics” at HCI International 2026 in Montreal, where our paper on AI-supported clinical handover was published.

  3. Took part in the Oxford Machine Learning Summer School (OxML 2026).

  4. “Agentic Design Patterns: A System-Theoretic Framework” appeared at the NeurIPS 2025 workshop on language, agent and world models (LAW).

  5. Completed an MSc in Financial Engineering at WorldQuant University.

  6. Third Prize at the Irish Collegiate Programming Contest (IrlCPC 2025).

  7. Released our survey “Multi-Agent Collaboration Mechanisms: A Survey of LLMs”.

Research

Reliable AI for clinical training

My thesis, Medical training analytics framework with enhanced feedback using Reliable AI methods, is carried out with UCC’s ASSERT Centre and the National Learning Analytics Unit, led by Prof. George Shorten.

LLM agents and multi-agent systems

I co-authored a survey of collaboration mechanisms in LLM-based multi-agent systems, and proposed a system-theoretic framework for agent design that breaks an agent into five functional subsystems and derives twelve reusable design patterns from them.

Earlier work

LLM-powered multimodal conversations for diabetes prevention, VinaLLaMA (a LLaMA-based Vietnamese foundation model), and, for my MSc capstone, deep learning for currency pair trading.

Publications

AI for medicine and health

Agents and language models

* Equal contribution. Citation counts are on Google Scholar.

Experience and education

2023 – 2027
PhD in Computer Science, University College Cork
Reliable AI Lab (RAIL). Research Ireland CRT-AI scholarship. Expected 2027.
2023 – 2025
MSc in Financial Engineering, WorldQuant University
2021 – 2023
AI Resident, FPT Software AI Center
Fine-tuned, deployed and evaluated LLMs for domain-specific chatbots (IVYChat); time-series models for motion-sickness analysis for Toyota Boshoku; research collaboration with UCC on AI for smart energy grids and code evaluation.
2021
AI Engineer Intern, Vingroup Big Data Institute
Speech classification models for the ViVi voice assistant in VinFast electric vehicles.
2018 – 2022
Computer Science, Hanoi University of Science and Technology
Certificate of Merit for excellent academic achievement, top 15 of the Class of 2022.

Service, awards and community

Service

Awards

Community