Publications

Publications in reversed chronological order.

2025

  1. SCALR@COLM ’25
    Maximizing Prefix-Confidence at Test-Time Efficiently Improves Mathematical Reasoning
    Matthias Otth, Jonas Hübotter, Ido Hakimi , and 1 more author
    In Workshop on Test-Time Scaling and Reasoning Models @ Conference on Language Modeling , 2025
  2. Test-time Offline Reinforcement Learning on Goal-related Experience
    Marco Bagatella*, Mert Albaba*Jonas Hübotter* , and 2 more authors
    arXiv preprint arXiv:2507.18809, 2025
  3. DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning
    Leander Diaz-Bone*, Marco Bagatella*Jonas Hübotter* , and 1 more author
    arXiv preprint arXiv:2505.19850, 2025
  4. COLM ’25
    Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging
    Ryo Bertolissi*Jonas Hübotter*, Ido Hakimi , and 1 more author
    In Conference on Language Modeling , 2025
  5. ICML ’25
    Active Fine-Tuning of Multi-Task Policies
    Marco Bagatella, Jonas Hübotter, Georg Martius , and 1 more author
    In International Conference on Machine Learning , 2025
  6. AISTATS ’25
    LITE: Efficiently Estimating Gaussian Probability of Maximality
    Nicolas Menet, Jonas Hübotter, Parnian Kassraie , and 1 more author
    In International Conference on Artificial Intelligence and Statistics , 2025
  7. ICLR ’25 Best Paper
    Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
    Jonas Hübotter, Sascha Bongni, Ido Hakimi , and 1 more author
    In International Conference on Learning Representations , 2025
    Best Paper Award at NeurIPS Workshop on Fine-Tuning in Modern Machine Learning, 2024.
  8. Probabilistic Artificial Intelligence
    Andreas Krause, and Jonas Hübotter
    arXiv preprint arXiv:2502.05244, 2025
  9. SODA ’25
    A Cut-Matching Game for Constant-Hop Expanders
    Bernhard Haeupler, Jonas Huebotter, and Mohsen Ghaffari
    In ACM-SIAM Symposium on Discrete Algorithms , 2025

2024

  1. NeurIPS ’24 Oral
    Transductive Active Learning: Theory and Applications
    Jonas Hübotter, Bhavya Sukhija, Lenart Treven , and 2 more authors
    In Advances in Neural Information Processing Systems , 2024
    Oral Presentation at ICML Workshop on Aligning Reinforcement Learning Experimentalists and Theorists, 2024.

2023

  1. NeurIPS ’23
    Efficient Exploration in Continuous-time Model-based Reinforcement Learning
    Lenart Treven, Jonas Hübotter, Bhavya Sukhija , and 2 more authors
    In Advances in Neural Information Processing Systems , 2023
  2. CoRL ’23
    Tuning Legged Locomotion Controllers via Safe Bayesian Optimization
    Daniel Widmer, Dongho Kang, Bhavya Sukhija , and 3 more authors
    In Conference on Robot Learning , 2023