Doctoral Researcher, Artificial Intelligence in Medical Imaging / Signal Analysis Lab
Evidence-aware AI systems for high-stakes work.
I build and study AI systems where the hard part is not only model output, but evidence, review, governance, and safe handoff: speech decision stability, clinical workflow support, agent governance, cybersecurity evidence, and practical AI systems education.
A public-safe synthesis of recent work across speech decision stability, clinical workflow support, AI triage demos, realtime voice systems, runtime governance, and AI systems engineering education.
UpdateLiquid Glass, visionOS, and AI point toward a future where the operating system is redefined less by the kernel than by a new operating surface for search, orchestration, and cross-app work.
EssayA research-oriented essay on cross-node fraud intelligence, minimal disclosure, and trustworthy AI design for high-stakes pattern formation under fragmented evidence.
EssayPackaged the AI Systems Engineering Handbook into a 7-day consulting-style onboarding path for enterprise voice AI, AI Gateway, agent governance, red teaming, K8s, GPU sizing, and customer acceptance evidence.
Teaching · 7-day Traditional Chinese tutorial with architecture, governance, security, deployment, and onboarding artifactsAdvanced a speech-to-decision stability research line that tests whether downstream decisions remain stable under plausible ASR alternatives.
Research · Selected-300 aggregate review complete; raw audio and transcripts remain privateDeveloped provenance-bounded evidence graph packet work for small-model decision support, with release gates, audit protocols, and public-benchmark orientation.
Research · Fallback package and validation gates ready for owner release-channel decisionBuilt a synthetic vital-aware intake and staff-review summary demo for a June market demonstration, with a narrow API contract and explicit clinical-scope controls.
System · Synthetic-data market demo; no autonomous diagnosis or production clinical triageHardened a urology previsit workflow prototype for adaptive question navigation, missing-field repair, clinician-review summaries, and PSA/CRM-ready proposal framing.
System · Synthetic-data workflow prototype for staff-review supportTurning manuscript and benchmark work into claim-gated evidence surfaces: CDS-ASR, PB-EGP/STV, TFSC false governability, and WISA CaseTrace.
Building narrow, reviewable systems that demonstrate the workflow before making larger claims: UroPrevisit Navigator, AI Triage Kiosk, Jarvis Voice Sight, and Project AURA.
Packaging AI systems engineering into practical learning artifacts: AI Gateway, agent governance, model serving, voice AI, cybersecurity, and enterprise delivery.
For research collaborators: start with Research and the recent evidence surfaces.
For healthcare or regulated-AI partners: start with Systems and the scope controls on each prototype.
For AI systems learners: start with Teaching, then read the 7-day enterprise voice AI onboarding path.
For hiring or review: start with Now and CV for the fastest current map.