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.
Packaged 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.
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.
Update · Recent Work / AI Systems / Trustworthy AILiquid 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.
Essay · Spatial Interface / visionOS / Liquid GlassA research-oriented essay on cross-node fraud intelligence, minimal disclosure, and trustworthy AI design for high-stakes pattern formation under fragmented evidence.
Essay · Trustworthy AI / Fraud Intelligence / Minimal Disclosure