Research

Think Reason Learn is the culmination of cutting-edge research spearheaded by Vela Research in close collaboration with Oxford University. This project integrates advanced AI techniques with interpretable machine learning to create transparent, high-performance models for complex classification tasks. For inquiries or collaboration opportunities, contact us at research@vela.partners.

Papers

• GPTree: Towards Explainable Decision-Making via LLM-powered Decision Trees

  Explores LLM-guided decision trees for dynamic feature generation.

  Research Team:

  Sichao Xiong Yigit Ihlamur Fuat Alican Aaron Ontoyin Yin

  📄 Paper: arXiv:2411.08257

• Random Rule Forest (RRF): Interpretable Ensembles of LLM-Generated Questions for Predicting Startup Success

  Develops ensembles of LLM-generated rules for transparent predictions.

  Research Team:

  Ben Griffin Diego Vidaurre Ugur Koyluoglu Joseph Ternasky Fuat Alican Yigit Ihlamur

  📄 Paper: arXiv:2505.24622