AI agents are transforming every industry — but enterprises still need trained professionals to guide them. MadGAA-LAB builds adversarial simulation environments that prepare your team before they go live, using intelligent AI agents across healthcare, finance, insurance, and customer service.
Physics background with 10+ years in industrial AI and system integration. Architect of the GAA simulation platform and multi-agent evaluation frameworks, spanning medical dialogue AI, LoRA behavioral modeling, and cross-industry digital twin systems.
Ph.D. in Medical Informatics, Research Fellow at MD Anderson Cancer Center. Specializes in healthcare big data, drug repurposing with deep learning, and single-cell genomics. 0+ peer-reviewed publications.
M.D. from National Cheng Kung University. Attending thoracic surgeon and Ph.D. candidate at Taipei Medical University. Focuses on uniportal VATS surgery, immune surveillance, and clinical AI research.
NTU M.S., Research Assistant at Harvard Medical School. 0+ peer-reviewed papers and 0+ citations. Specializes in EEG/BCI, Quantum ML, and multimodal AI. Former RLHF contributor at OpenAI.
Berlin-based French designer crafting modern, user-friendly web applications. Certified Wix Studio designer and Claude Code developer with real-world projects across e-commerce and healthcare.
PMP-certified Senior Program Manager with 8+ years driving complex technical programs across global markets. Expert in AI-driven development, SaaS platforms, and FinTech. Co-published at NVIDIA GTC 2025.
Stanford postdoctoral scholar, currently a researcher at NIMS (Japan). 0 journal publications, 0+ citations, H-index 0. Specializes in advanced battery technology and AI-driven materials science.
AI/ML engineer with 6+ years across speech synthesis, virtual humans, medical NLP, and clinical coding. NVIDIA GTC 2025 Poster Presenter and HIMSS Europe 2025 team representative.
M.S. student at NYCU, focusing on generative bio-language models and Physical AI. 3rd place in AgentX-AgentBeats Challenge (UC Berkeley). Full-stack developer with deep Agentic AI research experience.
The world's first cross-industry adversarial training simulation platform. Replaces expensive human role-players with intelligent AI agents — enabling scalable, measurable professional training for hospitals, banks, insurers, and contact centers. Built by a team with both clinical expertise and deep AI engineering capability.
Medical dialogue evaluation framework inspired by Objective Structured Clinical Examinations. Simulates 64 patient personas measuring Empathy, Persuasion, and Safety.
An LLM agents framework for interacting with FHIR databases, enabling structured clinical data retrieval and reasoning.
Public leaderboard for the OSCE evaluator within the AgentBeats challenge ecosystem. Compare medical agent performance across standardized clinical scenarios.
Adversarial security testing framework for AI agents. Evaluates robustness and safety against prompt injection and manipulation attacks.
Real-time voice-based clinical examination system extending the OSCE framework with speech interaction for realistic doctor-patient dialogue evaluation.
End-to-end LLM fine-tuning and knowledge distillation pipelines for domain-specific medical AI models. Building smaller, faster, and more accurate clinical language models.
