@article{hubotter2026reinforcement,title={Reinforcement Learning via Self-Distillation},author={Hübotter, Jonas and Lübeck, Frederike and Behric, Lejs and Baumann, Anton and Bagatella, Marco and Marta, Daniel and Hakimi, Ido and Shenfeld, Idan and Kleine Buening, Thomas and Guestrin, Carlos and Krause, Andreas},year={2026},journal={arXiv preprint arXiv:2601.20802},}
Self-Distillation Enables Continual Learning
Idan Shenfeld, Mehul Damani, Jonas Hübotter , and 1 more author
@article{shenfeld2026self,title={Self-Distillation Enables Continual Learning},author={Shenfeld, Idan and Damani, Mehul and Hübotter, Jonas and Agrawal, Pulkit},year={2026},journal={arXiv preprint arXiv:2601.19897},}
2025
Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning
Jonas Hübotter*, Leander Diaz-Bone*, Ido Hakimi , and 2 more authors
@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},}
ICLR ’26 Oral
Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models
Jonas Hübotter*, Patrik Wolf*, Alexander Shevchenko* , and 3 more authors
In International Conference on Learning Representations (2026) , 2025
Oral Presentation at NeurIPS 2025 Workshop on Continual and Compatible Foundation Model Updates.
@inproceedings{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},booktitle={International Conference on Learning Representations (2026)},}
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
@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)},}
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
@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)},}
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
@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)},}
COLM ’25
Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging
Ryo Bertolissi*, Jonas Hübotter*, Ido Hakimi , and 1 more author
@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)},}
@article{krause2025probabilistic,title={Probabilistic Artificial Intelligence},author={Krause, Andreas and Hübotter, Jonas},year={2025},journal={arXiv preprint arXiv:2502.05244},}
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
@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
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
@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)},}
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.
@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)},}
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.
@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
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
@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)},}
CoRL ’23
Tuning Legged Locomotion Controllers via Safe Bayesian Optimization
Daniel Widmer, Dongho Kang, Bhavya Sukhija , and 3 more authors
@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
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
@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)},}