publications

2025

  1. NeurIPS WS
    SCALAR: Self-Supervised Composition and Learning of Skills with LLM Planning and RL
    Renos Zabounidis, Yue Wu, Simon Stepputtis, and 3 more authors
    In NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models for Reasoning and Planning, 2025
    Best Paper HM Website
  2. NeurIPS WS
    Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning
    Renos Zabounidis, Aditya Golatkar, Michael Kleinman, and 3 more authors
    In NeurIPS 2025 Workshop on Efficient Reasoning, 2025
  3. Preprint
    Deception Is Its Own Reward: Multi-Agent Reinforcement Learning for Stratego with Theory of Mind
    Ini Ogontola, Renos Zabounidis, Joseph Campbell, and 2 more authors
    Preprint, 2025
  4. Preprint
    CDE: Concept-Driven Exploration for Reinforcement Learning
    Le Mao, Andrew H. Liu, Renos Zabounidis, and 2 more authors
    Preprint, 2025
    arXiv

2024

  1. Preprint
    Benchmarking and Enhancing Disentanglement in Concept-Residual Models
    Renos Zabounidis, Ini Ogontola, Joseph Campbell, and 2 more authors
    Preprint, 2024

2022

  1. CoRL
    Concept Policy Models for Interpretability in Multi Agent Reinforcement Learning
    Renos Zabounidis, Joseph Campbell, Dana Hughes, and 1 more author
    In 6th Conference on Robot Learning (CoRL), 2022

2021

  1. ACM
    Perceptions of Human and Machine Generated Articles
    Shubhra Tewari, Renos Zabounidis, Ammina Kothari, and 2 more authors
    ACM Digital Threats: Research and Practice, 2021

2020

  1. ICML WS
    Normalizing Flows Across Dimensions
    Edmond Cunningham, Renos Zabounidis, Abhinav Agrawal, and 2 more authors
    In ICML Workshop on Invertible Neural Networks and Normalizing Flows, 2020

2019

  1. IEEE BHI
    SmartDiagnostics: A Mobile Application for the Monitoring and Management of Movement Disorders
    Aparimit Chandra, Renos Zabounidis, Karine Tung, and 3 more authors
    In IEEE International Conference on Biomedical and Health Informatics (IEEE BHI), 2019