Research & Projects

Building explainable, safe, and trustworthy AI that ships into real systems.

Focus Areas

Explainable & Trustworthy AI

Frameworks that make AI decisions traceable and auditable, designed around emerging governance requirements such as the EU AI Act and ISO 13482.

XAIauditability

Safe Chain-of-Thought Reasoning

Defense-in-depth verification across structural, physical, semantic, and interpretability layers that detects hallucinated or unsafe reasoning before a robot acts.

LLM safetyrobotics

Interpretable Machine Learning

Neural-tree ensembles and other hybrid architectures for robust, explainable prediction under sensor noise and missing data.

neural treesrobustness

Applied LLM Systems (PropTech / LegalTech)

Retrieval-grounded, compliance-aware LLM systems with citation-backed explanations and jurisdiction-aware safety guardrails.

RAGguardrails

Selected Projects

  • 2020–

    Vardenus: AI-driven PropTech & LegalTech Platform

    Co-Founder & CTO, Vardenus

    Leading the technical vision for an AI- and blockchain-based real-estate platform: an LLM and retrieval "AI-Lawyer" mediation module with citation-grounded, jurisdiction-aware guidance; compliance-aware safety guardrails; tokenized property workflows; and scalable cloud and MLOps infrastructure. Recognized with a 2025 Global Recognition Award (Real Estate Technology).

    LLMRAGPropTechblockchain
  • 2025

    AlimGPT: Clinical RAG Assistant for Dentistry

    Creator · production retrieval-augmented LLM system

    A retrieval-augmented generation assistant for dentistry that grounds every answer in clinical sources to minimize hallucination. Built on a production stack of Render, Supabase, Qdrant vector search, and Voyage AI embeddings.

    RAGhealthcarevector search
  • 2026

    CT-SAFR: Safe & Interpretable Chain-of-Thought for Robots

    Research · presented at IEEE CAI 2026

    A defense-in-depth, multi-layered verification framework addressing the faithfulness problem in Chain-of-Thought-enabled autonomous robots. It reported 94% detection of unsafe and hallucinated reasoning at sub-500 ms latency in a warehouse-robot case study, and is covered by a pending U.S. provisional patent.

    CoT safetyverification
  • 2026

    TRACE: Transparent Reasoning Architecture for Autonomous Robots

    Research · IEEE SoutheastCon 2026

    A model-agnostic, four-layer decision framework that traces every autonomous action back to sensor evidence via documented causal chains, with high evidence-traceability and decision-reconstructability across simulated decision cycles.

    explainabilityautonomy
  • 2025

    Explainable Neural Trees for Remaining-Useful-Life Prediction

    Research · turbofan engine prognostics (NASA C-MAPSS)

    An explainable neural-tree ensemble with "sensor-dropout augmentation" for robust remaining-useful-life prediction under sensor noise and missing data. It achieves strong accuracy with gradient-based feature-importance explanations and large gains in fault tolerance.

    prognosticsinterpretability

Open-Source Software

  • PyPI

    neural-trees

    scikit-learn-compatible PyTorch · Soft Decision Trees, HMoE, 5×2cv F-test · MIT · 30★

    A scikit-learn-compatible library of PyTorch implementations of soft decision trees and hierarchical mixtures of experts, with statistical model-comparison tests. Install with pip install neural-trees.

    PyPI versionPyPI downloadsGitHub stars

    PyPIGitHubLive demo
  • GitHub

    cognitest-framework

    LLM-assisted cognitive software-testing framework

    An LLM-assisted test-automation framework exploring cognitive approaches to software testing, related to the verification ideas behind CT-SAFR.

    GitHub
  • GitHub

    ml-playground

    Interactive ML model-comparison playground

    An interactive playground comparing scikit-learn, XGBoost, LightGBM, CatBoost, TabNet, and neural-trees side by side, with 5×2cv significance testing.

    Live demoGitHub
  • GitHub

    turbofan-explainable-neural-trees

    Code · explainable neural trees for RUL prediction (IEEE SMC 2026)

    Reference implementation of explainable neural-tree models for remaining-useful-life prediction on the NASA C-MAPSS benchmark.

    Live demoGitHub
See full publications → See patents →