Publications and Preprints

$^\star$ equal contribution

2026

• Aligning Language Models from User Interactions [paper, project, code]
  Thomas Kleine Buening, Jonas Hübotter, Barna Pásztor, Giorgia Ramponi, Andreas Krause

• MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference [paper]
  Raphaël Baur, Yannick Metz, Maria Gkoulta, Menna El-Assady, Giorgia Ramponi, Thomas Kleine Buening
  ICML 2026

• Reinforcement Learning via Self-Distillation [paper, project, code]
  Jonas Hübotter, Frederike Lübeck, Lejs Behric, Anton Baumann, Marco Bagatella, Daniel Marta, Ido Hakimi, Idan Shenfeld, Thomas Kleine Buening, Carlos Guestrin, Andreas Krause
  ICML 2026, Best Paper Award at the TTU Workshop (ICLR 2026)

2025

• Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game [paper]
  Barna Pásztor, Thomas Kleine Buening, Andreas Krause
  ICLR 2026

• Causal Imitation Learning under Expert-Observable and Expert-Unobservable Confounding [paper]
  Daqian Shao, Thomas Kleine Buening, Marta Kwiatkowska
  ICLR 2026

• Strategyproof Reinforcement Learning from Human Feedback [paper]
  Thomas Kleine Buening, Jiarui Gan, Debmalya Mandal, Marta Kwiatkowska
  NeurIPS 2025

• Data Source Adaptive Online Learning under Heteroscedastic Noise [paper]
  Amith Anan, Aadirupa Saha, Thomas Kleine Buening, Haipeng Luo
  OPT 2025: 17th Annual Workshop on Optimization for Machine Learing

• A Minimax Approach to Ad Hoc Teamwork [paper]
  Victor Villin, Thomas Kleine Buening, Christos Dimitrakakis
  AAMAS 2025

2024

• Strategic Linear Contextual Bandits [paper]
  Thomas Kleine Buening, Aadirupa Saha, Christos Dimitrakakis, Haifeng Xu
  NeurIPS 2024

• Environment Design for Inverse Reinforcement Learning [paper]
  Thomas Kleine Buening$^\star$, Victor Villin$^\star$, Christos Dimitrakakis
  ICML 2024, Oral Presentation

• Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation [paper]
  Thomas Kleine Buening, Aadirupa Saha, Christos Dimitrakakis, Haifeng Xu
  ICLR 2024, Spotlight Presentation

2023

• Minimax-Bayes Reinforcement Learning [paper]
  Thomas Kleine Buening$^\star$, Christos Dimitrakakis$^\star$, Hannes Eriksson$^\star$, Divya Grover$^\star$, Emilio Jorge$^\star$
  AISTATS 2023

• An Improved Dynamic Regret Algorithm for Adaptive Non-Stationary Dueling Bandits [paper]
  Thomas Kleine Buening, Aadirupa Saha
  AISTATS 2023

2022

• Interactive Inverse Reinforcement Learning for Cooperative Games [paper]
  Thomas Kleine Buening, Anne-Marie George, Christos Dimitrakakis
  ICML 2022, Best Paper Award at the Cooperative AI Workshop (NeurIPS 2021)

• On Meritocracy in Optimal Set Selection [paper]
  Thomas Kleine Buening, Meirav Segal, Debabrota Basu, Anne-Marie George, Christos Dimitrakakis
  EEAMO 2022, Best Student Paper Award