GPTree
Explainable decision-making via LLM-powered decision trees, designed for practical, human-in-the-loop workflows.
Aaron Ontoyin Yin
AI Engineer & Researcher
My goal is to make humans wow at machines.
Research
My research interests is in discovering new ways to make machines do what humans do.
- Deep learning, RL for real-world problems
- Robotics and control (learning in embodied environments)
- LLM-powered decision systems and human-in-the-loop learning
- Interpretable ML and XAI
- Quantum computing (actively learning)
Selected Work
Think Reason Learn
Open-source library combining large language models with interpretable ML to build transparent decision systems.
Dual Approach in Autonomous Directional Drilling
Research on autonomous directional drilling, combining Drillbotics hardware innovations with a virtual rig simulator.
Publications
-
GPTree: Towards Explainable Decision-Making via LLM-powered Decision Trees
-
GPT-HTree: A Decision Tree Framework Integrating Hierarchical Clustering and Large Language Models for Explainable Classification
-
VCBench: Benchmarking LLMs in Venture Capital
-
From Limited Data to Rare-event Prediction: LLM-powered Feature Engineering and Multi-model Learning in Venture Capital
-
Dual Approach in Autonomous Directional Drilling: Innovations with Drillbotics 1.5 Inch Automated RSS and Virtual Rig Platforms
-
LLM-AR: LLM-powered Automated Reasoning Framework
Open-source & Projects
News
-
2025
New benchmark released for evaluating LLMs in venture capital.
-
2025
VCBench accepted for a computing conference (2026), London.
-
2024
Best Student in Software Engineering - UMaT Excellence Awards.
-
2023
UMaT tops Virtual Category of Drillbotics - JoyNews.
