Liv G. d'Aliberti

Computer Science Ph.D. Student at Princeton University.

Liv G. d'Aliberti

Room 320C, the Messiest Cubicle

Sherrerd Hall

Princeton, NJ, 08544

Advised by Manoel Horta Ribeiro and affiliated with the Humans and Machines (HAM) Lab and Center for Information Technology Policy, I study how learned agents reason, decide, and change behavior, focusing on reliability, interpretability, and empirically grounded evaluation at scale.

  • research
    • Reinforcement learning
    • Machine learning
    • Reliable reasoning
  • current threads
    • Diverse reasoning
    • Judgemental forecasting
    • Agentic misalignment
  • previous life
    • Government R&D
    • Privacy
    • Autonomy

Prior to starting my Ph.D., I worked as a research scientist at Leidos in their CTO Office Artificial Intelligence & Machine Learning Accelerator. I am also a Lecturer in Computer Science at Johns Hopkins Engineering for Professionals, where I teach courses in modern Python software development and deep learning with PyTorch. I earned my Master of Science in Applied Mathematics and Statistics in 2019.

I really like all cats and one dog, my wife’s cavapoo. When I’m offline, I’m usually hiking, backpacking, skiing, or exploring new places.

news

Jun 17, 2026 Workshop paper accepted at AutoRL at RLC 2026: Behavior-Consistent Deep Reinforcement Learning.
May 26, 2026 I passed my Princeton C.S. generals exam!
May 20, 2026 Preprint released: Behavior-Consistent Deep Reinforcement Learning.
Apr 06, 2026 Paper accepted to Findings of ACL: The Illusion of Insight in Reasoning Models.
Mar 26, 2026 Patent published: HOLOGRAPHIC GRAPH TRANSFORMER NETWORK (HGTN) SYSTEM AND METHOD.

selected publications

  1. Behavior-Consistent Deep Reinforcement Learning
    Marcel Hussing ,  Liv G. d’Aliberti ,  Claas Voelcker, and 2 more authors
    In Workshop on Automated Reinforcement Learning at RLC, 2026
    Accepted
  2. The Illusion of Insight in Reasoning Models
    Liv G. d’Aliberti  and  Manoel Horta Ribeiro
    In Findings of the Association for Computational Linguistics: ACL 2026, Jul 2026
  3. Explainability for Unmanned Aerial Vehicle Control via Multi-Objective Reinforcement Learning
    Christian A. Clark ,  Kevin M. Albarado ,  Joshua P. Wilson, and 3 more authors
    In 2025 IEEE Aerospace Conference, Jul 2025
  4. Grounded-Retrieval Adversarial Imitation Loop: Integrating Language, Agent, and World Models
    Liv G. d’Aliberti  and  Manoel Horta Ribeiro
    In NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models for Reasoning and Planning, Jul 2025