Profile photo

Kleyton da Costa

AI Researcher · Ph.D. Student @ UCL

kleyton.vsc@gmail.com · kleyton.costa@holisticai.com · kleyton.costa.25@ucl.ac.uk

I'm a Ph.D. Student in Computer Science at University College London, advised by Prof. Philip Treleaven and Prof. Dimitrios Kanoulas, where my research focus on predictive safety in embodied AI , methods for anticipating unsafe behavior in physical and decision-making agents.

I'm currently an AI Researcher and Engineer at Holistic AI and a core contributor to open-source research software for AI trustworthiness, optimization, and state-space modeling.

Recent Publications

All publications →

  1. When Should Graph Attention Be Sparse? Learning a Per-Edge Tsallis Index

    2026

    Kleyton da Costa, Bernardo Modenesi

    PDFProject page

  2. Perspectives on Tsallis Statistics for Artificial Intelligence

    2026

    Kleyton da Costa, Bernardo Modenesi

    PDFProject page

  3. GraphNetz: Statistical Benchmarking of Graph Neural Networks with Paired Tests and Rank Aggregation

    2026

    Kleyton da Costa, Bernardo Modenesi

    arXiv

    PDFProject page

  4. A Survey on Predictive Safety in Embodied AI

    2026

    Kleyton da Costa, Adriano Koshiyama, Dimitrios Kanoulas, Philip Treleaven

    SSRN

    PDFProject page

  5. Divergence-Guided Particle Swarm Optimization

    2026

    Kleyton da Costa, Bernardo Modenesi, Ivan F. M. Menezes, Hélio Lopes

    arXiv

    PDF

Education

  • Ph.D. in Computer Science · University College London
    2026 — 2030
  • M.Sc. in Computer Science · PUC-Rio
    2023 — 2025
  • B.Sc. in Economics · UFRRJ
    2017 — 2021

Affiliations

  • AI Researcher & Engineer · Holistic AI
    Aug 2021 — Present
  • Researcher · PUC-Rio (funded by Petrobras)
    Mar 2023 — Aug 2025
  • Data Scientist · State Government of Rio de Janeiro
    Jan 2022 — Mar 2023

Contact

For research collaboration, academic discussion, or open-source contributions, reach me at kleyton.vsc@gmail.com.