Research publications

Publications timeline

  1. This work was supported by UBS Switzerland AG and its affiliates through the UBS-IDSIA AI Lab.

    Automatic Prompt Optimization for Dataset-Level Feature Discovery

    Authors: Adrian Cosma, Oleg Szehr, David Kletz, Alessandro Antonucci, Olivier Pelletier

      DOI

    • This work was supported by UBS Switzerland AG and its affiliates through the UBS-IDSIA AI Lab.

      Test-Time Collective Classification over Multi-Agent Networks

      Authors: Ping Hu, Mert Kayaalp, Ali H. Sayed

      • Conference
      • San Diego, US
      • NeurIPS Workshop on Algorithmic Collective Action

    • This work was supported by UBS Switzerland AG and its affiliates through the UBS-IDSIA AI Lab.

      Assessing RAG System Capabilities on Financial Documents

      Authors: Oscar Lithgow-Serrano, David Kletz, Vani Kanjirangat, David Adametz, Marzio Lunghi, Claudio Bonesana, Matilde Tristany-Farinha, Yuntao Li, Detlef Repplinger, Marco Pierbattista, Stefania Stan, Oleg Szehr

      • Conference
      • Association for Computational Linguistics
      • Pages: 124–147
      • Suzhou, China
      • 10th Workshop on Financial Technology and Natural Language Processing (FinNLP 2025), co-located with EMNLP 2025
      DOIGitHub

    • This work was supported by UBS Switzerland AG and its affiliates through the UBS-IDSIA AI Lab.

      Causal Understanding by LLMs: The Role of Uncertainty

      Authors: Oscar Lithgow-Serrano, Vani Kanjirangat, Alessandro Antonucci

      • Association for Computational Linguistics
      • Pages: 208-228
      • Proceedings of the 2nd Workshop on Uncertainty-Aware NLP (UncertaiNLP 2025)
      DOI

    • Deep Hedging Under Non-Convexity: Limitations and a Case for AlphaZero

      Authors: Matteo Maggiolo, Giuseppe Nuti, Miroslav Štrupl, Oleg Szehr

      • Preprint (arXiv)
      DOI

    • This work was supported by UBS Switzerland AG and its affiliates through the UBS-IDSIA AI Lab.

      Causal Understanding by LLMs: The Role of Uncertainty

      Authors: Oscar Lithgow-Serrano, Vani Kanjirangat, Alessandro Antonucci

      • Preprint
      • Suzhou, China
      • 2nd Workshop on Uncertainty-Aware NLP (UncertaiNLP 2025), co-located with EMNLP 2025
      DOI

    • A Quantum Perspective on Uniqueness Pairs for the Fourier Transform

      Authors: Oleg Szehr

        DOI

      • This work was supported by UBS Switzerland AG and its affiliates through the UBS-IDSIA AI Lab.

        Minimizing the Probability of Error for Decision Making over Graphs

        Authors: Ping Hu, Mert Kayaalp, Ali H. Sayed

        • Journal
        • Institute of Electrical and Electronics Engineers (IEEE)
        • Pages: 1-22
        DOI

      • On the Convergence and Stability of Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning, and Online Decision Transformers

        Authors: Miroslav Štrupl, Oleg Szehr, Francesco Faccio, Dylan R. Ashley, Rupesh Kumar Srivastava, Jürgen Schmidhuber

        • Preprint
        DOI

      • Hedging using reinforcement learning: Contextual k-armed bandit versus Q-learning

        Authors: Loris Cannelli, Giuseppe Nuti, Marzio Sala, Oleg Szehr

        • Journal Article
        DOI

      • Hedging of financial derivative contracts via Monte Carlo tree search

        Authors: Oleg Szehr

        • Journal Article
        • Pages: 47-80
        DOI

      • Overfitting in portfolio optimization

        Authors: Matteo Maggiolo, Oleg Szehr

        • Journal Article
        • Pages: 1-33
        DOI