avatar

Niko Lorantos

University of Massachusetts Amherst
nlorantos (at) umass (dot) edu


I study mathematical computing and philosophy with honors at UMass Amherst. My primary research interests involve open-ended agents. This summer I’m conducting research on AI alignment, and tuning ecosystem models at Woodwell Climate Research Center. In the past I’ve worked on evolutionary algorithms and artificial life with Lee Spector at Amherst College, engineered language models at UMass CICS, and finetuned structural biology models at a biotech startup.

In my free time I enjoy snowboarding, listening to music, and spending time in nature.

Research

  1. RLC
    Toward Aligned Open-Endedness in AI Systems

    Niko Lorantos

    Reinforcement Learning Conference Finding the Frame Workshop 2026 (To appear)
    We show that alignment and open-endedness are largely incompatible and identify specific demands open-endedness places beyond existing alignment methods.

  2. arXiv
    Adaptive Exploration in Lenia with Intrinsic Multi-Objective Ranking

    Niko Lorantos, Lee Spector

    arXiv
    We evolve populations of Lenia artificial life through intrinsic objectives to promote diversity, emergent complexity, and open-endedness.
    PDF arXiv Code

  3. GPTP XXII
    Evolution of Artificial Intelligence, Continued

    Lee Spector, Ryan Bahlous-Boldi, Paul Vander Vort, Niko Lorantos

    Genetic Programming Theory & Practice XXII
    We outline significant advancements in AI driven by evolution, particularly in neural architecture design and preference learning.
    Book

  4. IC2S2
    Estimating Support for US Presidential Candidates Using X Polls

    Bagchi, Sunil, Khojaste, Kalakonnavar, Lorantos, Samory, Yang, Grabowicz

    12th International Conference on Computational Social Science