ΛάΓ

ΛάΓ laboratory

Institute of ΛάΓ

Λ

Lithos

Λίθος

The immutable physical foundation.

ά

Asklepios

Ἀσκληπιός

The sovereign art of healing.

Γ

Gnome

Γνώμη

The intent that guides intelligence.

Section 1

About

The most critical challenge facing modern healthcare is the catastrophic waste of human capital.

The intellect of highly trained physicians is buried under a deluge of repetitive patterns in routine primary care—draining resources from complex decision-making and genuine medical inquiry.

Our answer is Autonomous Triage: not the replacement of clinical judgment, but its liberation. By grounding AI behavior in physical law rather than statistical correlation, we build systems that know why a patient is deteriorating—not merely that they are. Systems that can refuse unsafe interventions on principled grounds. Systems that return intelligence to where it belongs.

We translate this conviction into research, intellectual property, and products.

Section 2

Research & Services

  • Fundamental Research

    Exploratory studies at the intersection of computational science and clinical medicine, focusing on causal inference, neuro-symbolic AI, and continuous biosignal estimation.

  • Product Development

    Consumer and clinical-grade applications that translate research into daily use—from infant care tracking to non-invasive diagnostics.

  • Intellectual Property

    Strategic acquisition and protection of research technologies emerging from our investigative work.

Section 3

Investigator

Leon Moriguchi

Investigator & Founder, Institute of ΛάΓ

Born April 2, 2008, Kagoshima, Japan — Based in Fukuoka

Leon Moriguchi lives at the intersection of two worlds that rarely speak to each other: the rigor of computational science and the urgency of clinical medicine. He is neither purely a researcher nor purely a builder—he is both, by necessity.

His conviction is simple: the most critical bottleneck in modern healthcare is not the absence of data, but the absence of frameworks capable of reasoning about it physically and causally. Every project he pursues is an attempt to close that gap—from continuous biosignal estimation in daily life, to non-invasive ophthalmic sensing from a smartphone camera, to the architectural foundations of AI that refuses unsafe interventions on physical grounds.

At 17, he has presented original research at an international conference in Singapore, is founding a Delaware C-Corporation, and is preparing a submission to NeurIPS 2026.

Background

  1. 2008Born in Kagoshima, Japan
  2. PrimaryAttended Japanese school in Kuala Lumpur
  3. 20249-month overseas research period — San Diego, Boston, Berlin
  4. 2025CEFR C2 English certification
  5. PresentEnrolled at a Japanese high school in Fukuoka

Active Projects

  • DElenchus

    Neuro-Symbolic AI for Safety-Critical Cyber-Physical Systems

    A physics-grounded agent that treats safety as a structural invariant rather than a reward signal. Built on Monotonic Neural ODEs and Active Inference with Hierarchical Markov Blankets. Targets fault localization and epistemic refusal in systems governed by physical law. Submission to NeurIPS 2026 in preparation.

  • Project Trinity

    Non-Invasive Continuous Biosignal Estimation

    A pilot study investigating the estimation of blood pressure and blood glucose from PPG signals using Neural ODEs and multimodal sensor fusion.

  • OcularEVM

    Smartphone-Based Intraocular Pressure Estimation

    Detection of post-saccadic oscillation (PSO) from iPhone 15 Pro footage at 15Hz—potentially a world-first for smartphone-based PSO detection. Target accuracy: ±3mmHg for non-invasive IOP estimation.

  • めもり / Memori

    AI-Powered Infant Care for iOS

    A consumer iOS application combining ambient UX design, computer vision, and medical-grade logging. Targets the Japanese babycare market with a long-term vision toward pediatric health data infrastructure.

Selected Publications & Presentations

  1. [1]
    From Black-Box to Glass-Box: Knowledge-Constrained Neuro-Symbolic Acute Pharyngitis Triage under Data Scarcity

    Research Square (preprint), 2026. Oral presentation at ICRLSH 2026, Singapore.

  2. [2]

    DElenchus: Dynamic, Differential, Deep Active Inference with Hierarchical Markov Blankets for Causal Discovery

    In Preparation, 2026

Affiliations

  • Founder & Investigator, Institute of ΛάΓ2026/4/2 —
Section 4

Contact

For inquiries regarding research partnerships or IP licensing, please contact us.