Publications

2025

1. Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning

   Jonas Hübotter^*, Leander Diaz-Bone^*, Ido Hakimi , and 2 more authors

   arXiv preprint arXiv:2510.04786, 2025

   Bib PDF Code Models Data

   @article{hubotter2025learning,
     title = {Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning},
     author = {Hübotter, Jonas and Diaz-Bone, Leander and Hakimi, Ido and Krause, Andreas and Hardt, Moritz},
     year = {2025},
     journal = {arXiv preprint arXiv:2510.04786},
   }

2. Oral

   Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models

   Jonas Hübotter^*, Patrik Wolf^*, Alexander Shevchenko^* , and 3 more authors

   arXiv preprint arXiv:2509.24510, 2025

   Oral Presentation at NeurIPS 2025 Workshop on Continual and Compatible Foundation Model Updates.
   

   Bib PDF Code Models

   @article{hubotter2025specialization,
     title = {Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models},
     author = {Hübotter, Jonas and Wolf, Patrik and Shevchenko, Alexander and Jüni, Dennis and Krause, Andreas and Kur, Gil},
     year = {2025},
     journal = {arXiv preprint arXiv:2509.24510},
   }

3. 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) , 2025

   Bib PDF Poster

   @inproceedings{otth2025maximizing,
     title = {Maximizing Prefix-Confidence at Test-Time Efficiently Improves Mathematical Reasoning},
     author = {Otth, Matthias and Hübotter, Jonas and Hakimi, Ido and Krause, Andreas},
     year = {2025},
     booktitle = {Workshop on Test-Time Scaling and Reasoning Models @ Conference on Language Modeling (2025)},
   }

4. EWRL ’25

   Test-time Offline Reinforcement Learning on Goal-related Experience

   Marco Bagatella^*, Mert Albaba^*, Jonas Hübotter , and 2 more authors

   In European Workshop on Reinforcement Learning (2025) , 2025

   Bib PDF Code

   @inproceedings{bagatella2025test,
     title = {Test-time Offline Reinforcement Learning on Goal-related Experience},
     author = {Bagatella, Marco and Albaba, Mert and Hübotter, Jonas and Martius, Georg and Krause, Andreas},
     year = {2025},
     booktitle = {European Workshop on Reinforcement Learning (2025)},
   }

5. NeurIPS ’25

   DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning

   Leander Diaz-Bone^*, Marco Bagatella^*, Jonas Hübotter^* , and 1 more author

   In Advances in Neural Information Processing Systems (2025) , 2025

   Bib PDF Code

   @inproceedings{diazbone2025discover,
     title = {DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning},
     author = {Diaz-Bone, Leander and Bagatella, Marco and Hübotter, Jonas and Krause, Andreas},
     year = {2025},
     booktitle = {Advances in Neural Information Processing Systems (2025)},
   }

6. 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) , 2025

   Bib PDF Code Models Poster

   @inproceedings{bertolissi2025local,
     title = {Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging},
     author = {Bertolissi, Ryo and Hübotter, Jonas and Hakimi, Ido and Krause, Andreas},
     year = {2025},
     booktitle = {Conference on Language Modeling (2025)},
   }

7. Probabilistic Artificial Intelligence

   Andreas Krause, and Jonas Hübotter

   arXiv preprint arXiv:2502.05244, 2025

   Bib PDF

   @article{krause2025probabilistic,
     title = {Probabilistic Artificial Intelligence},
     author = {Krause, Andreas and Hübotter, Jonas},
     year = {2025},
     journal = {arXiv preprint arXiv:2502.05244},
   }

8. 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) , 2025

   Bib PDF Code Poster

   @inproceedings{menet2025lite,
     title = {LITE: Efficiently Estimating Gaussian Probability of Maximality},
     author = {Menet, Nicolas and Hübotter, Jonas and Kassraie, Parnian and Krause, Andreas},
     year = {2025},
     booktitle = {International Conference on Artificial Intelligence and Statistics (2025)},
   }

2024

1. 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) , 2024

   Bib PDF Code Poster

   @inproceedings{bagatella2024active,
     title = {Active Fine-Tuning of Multi-Task Policies},
     author = {Bagatella, Marco and Hübotter, Jonas and Martius, Georg and Krause, Andreas},
     year = {2024},
     booktitle = {International Conference on Machine Learning (2025)},
   }

2. 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) , 2024

   Best Paper Award at NeurIPS 2024 Workshop on Fine-Tuning in Modern Machine Learning.
   

   Bib PDF Code Poster Slides

   @inproceedings{hubotter2024efficiently,
     title = {Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs},
     author = {H{\"u}botter, Jonas and Bongni, Sascha and Hakimi, Ido and Krause, Andreas},
     year = {2024},
     booktitle = {International Conference on Learning Representations (2025)},
   }

3. 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) , 2024

   Oral Presentation at ICML 2024 Workshop on Aligning Reinforcement Learning Experimentalists and Theorists.
   

   Bib PDF Code Poster Slides

   @inproceedings{hubotter2024transductive,
     title = {Transductive Active Learning: Theory and Applications},
     author = {H{\"u}botter, Jonas and Sukhija, Bhavya and Treven, Lenart and As, Yarden and Krause, Andreas},
     year = {2024},
     booktitle = {Advances in Neural Information Processing Systems (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) , 2023

   Bib PDF

   @inproceedings{treven2023efficient,
     title = {Efficient Exploration in Continuous-time Model-based Reinforcement Learning},
     author = {Treven, Lenart and H{\"u}botter, Jonas and Sukhija, Bhavya and D{\"o}rfler, Florian and Krause, Andreas},
     year = {2023},
     booktitle = {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) , 2023

   Bib PDF Video Code

   @inproceedings{widmer2023tuning,
     title = {Tuning Legged Locomotion Controllers via Safe Bayesian Optimization},
     author = {Widmer, Daniel and Kang, Dongho and Sukhija, Bhavya and H{\"u}botter, Jonas and Krause, Andreas and Coros, Stelian},
     year = {2023},
     booktitle = {Conference on Robot Learning (2023)},
   }

2022

1. 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) , 2022

   Bib PDF

   @inproceedings{haeupler2022cut,
     title = {A Cut-Matching Game for Constant-Hop Expanders},
     author = {Haeupler, Bernhard and Huebotter, Jonas and Ghaffari, Mohsen},
     year = {2022},
     booktitle = {ACM-SIAM Symposium on Discrete Algorithms (2025)},
   }