CV

Curriculum vitae for Liv G. d'Aliberti, Computer Science Ph.D. student at Princeton University.

General Information

Full Name Liv G. d'Aliberti
Role Computer Science Ph.D. Student, Princeton University
Research Areas Reinforcement learning, machine behavior, reliable AI reasoning, interpretable decision-making systems
Links

Education

  • 2024-present
    Ph.D. in Computer Science
    Princeton University
    • Advised by Manoel Horta Ribeiro.
    • Affiliated with the Humans and Machines Lab and Princeton CITP.
  • 2019
    M.S. in Applied Mathematics and Statistics
    Georgetown University
  • 2017
    B.A. / B.S. in History (Honors) and Mathematics
    Georgetown University
    • Minor in Economics.

Research Experience

  • 2024-present
    Ph.D. Student
    Humans and Machines Lab and Center for Information Technology Policy, Princeton University
    • Researching reliable, interpretable, and empirically grounded AI reasoning and decision-making.
    • Current work focuses on learned-agent behavior, reinforcement learning stability, and behavioral consistency.
  • 2019-2024
    Senior AI/ML Researcher
    Leidos Inc.
    • Led and contributed to AI/ML research programs across reinforcement learning, autonomy, privacy-enhancing technologies, and explainable decision-making.
    • Helped transition internal research into customer-funded projects.
    • Supported intern program development and research team growth.
  • 2018-2019
    Data Analyst
    Model B
    • Developed analytics workflows for campaign-based marketing data.

Selected Publications

  • 2026
    Behavior-Consistent Deep Reinforcement Learning
    Workshop on Automated Reinforcement Learning at RLC
  • 2026
    The Illusion of Insight in Reasoning Models
    Findings of the Association for Computational Linguistics: ACL 2026
  • 2025
    Grounded-Retrieval Adversarial Imitation Loop
    NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models for Reasoning and Planning
  • 2025
    Explainability for Unmanned Aerial Vehicle Control via Multi-Objective Reinforcement Learning
    2025 IEEE Aerospace Conference
  • 2022
    Preserving Patient Privacy during Computation over Shared Electronic Health Record Data
    Journal of Medical Systems

Teaching

  • 2025-2026
    Deep Learning Developments with PyTorch
    Johns Hopkins Engineering for Professionals
    • Instructor for Spring, Summer, and Fall 2025; Spring, Summer, and Fall 2026.
  • 2024-2026
    Modern Software Concepts in Python
    Johns Hopkins Engineering for Professionals
    • Instructor for Summer and Fall 2024; Summer and Fall 2025; Spring, Summer, and Fall 2026.
  • 2023-2024
    Introduction to Programming
    Johns Hopkins Engineering for Professionals
    • Instructor for Spring, Summer, and Fall 2023; Summer and Fall 2024.
  • Fall 2026
    Computer Vision (COS 429)
    Princeton University
    • Teaching Assistant with Prof. Olga Russakovsky.
  • Teaching Assistant
    Georgetown University
    • Teaching assistant in the Department of Mathematics and Statistics.
    • Data Mining, one semester.
    • Computational Mathematics, two semesters.

Selected Talks

  • 2026
    Learning Machine Behavior: Measuring Exploration, Stability, and Alignment in Learned Agents
    Princeton Computer Science General Exam

Profiles and Features

  • 2026
    Lecturer Profile
    Johns Hopkins Engineering for Professionals
  • 2026
    M.S. Alumni Profile
    Georgetown University Department of Mathematics and Statistics

Honors and Awards

  • 2024
    Leidos CTO Office Purple Dollar Award
    Recognized for successful transition of internal research to customer-funded projects.
  • 2021
    Leadership, Excellence in Integrity - Rising Star
    Leidos Annual Achievement Award
    Recognized for leadership potential.

Patents and Invention Disclosures

Academic Interests

  • Reliable Learned Agents
    • Measuring and improving behavioral consistency across reinforcement learning runs.
    • Understanding when learned systems change behavior in ways that matter.
  • AI Reasoning and Decision-Making
    • Empirical evaluation of reasoning models.
    • Interpretable, auditable, and reliable decision-making systems.
  • Privacy and Applied ML
    • Privacy-enhancing technologies.
    • Secure and explainable AI systems for high-stakes settings.