publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. Preprint
    Reason in Style: Discovering and Controlling Style in Language Models
    Ioana Marinescu, Eric Karl Oermann, and Kyunghyun Cho
    2026
  2. Psych Review
    Neural Networks Can Capture Human Concept Learning when Trained with Symbolic Priors
    Ioana Marinescu, R. Thomas McCoy, and Thomas L. Griffiths
    Psychological Review, 2026
    In press
  3. ICML Workshop
    On the Relationship Between the Choice of Representation and In-Context Learning
    Ioana Marinescu, Kyunghyun Cho, and Eric Karl Oermann
    In ICML 2026 Workshop on Foundations of Deep Generative Models, 2026

2025

  1. CogSci
    Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks
    Gianluca Bencomo, Max Gupta, Ioana Marinescu, and 2 more authors
    2025

2024

  1. CogSci
    Distilling Symbolic Priors for Concept Learning into Neural Networks
    Ioana Marinescu, R. Thomas McCoy, and Thomas L. Griffiths
    2024
  2. JOSS
    AutoRA: Automated Research Assistant for Closed-Loop Empirical Research
    Sebastian Musslick, Benjamin Andrew, Chad C Williams, and 6 more authors
    2024
  3. Preprint
    Human and Automatic Interpretation of Romanian Noun Compounds
    Ioana Marinescu and Christiane Fellbaum
    2024

2023

  1. NeurIPS AI4Science
    GFN-SR: Symbolic Regression with Generative Flow Networks
    Sida Li, Ioana Marinescu, and Sebastian Musslick
    2023
  2. NeurIPS AI4Science
    Expression Sampler as a Dynamic Benchmark for Symbolic Regression
    Ioana Marinescu, Younes Strittmatter, Chad Williams, and 1 more author
    2023
  3. NeurIPS AI4Science
    Bayesian Machine Scientist for Model Discovery in Psychology
    Joshua Hewson, Younes Strittmatter, Ioana Marinescu, and 2 more authors
    2023