Publications
* denotes equal contribution.
2026
- Aligning Language Models from User InteractionsConference on Language Modeling (2026)Oral Presentation at ICML 2026 Workshop on Continual Adaptation at Scale.pdfwebsitecodethread
bibtex
@inproceedings{kleinebuening2026aligning, title = {Aligning Language Models from User Interactions}, author = {Kleine Buening, Thomas and Hübotter, Jonas and Pásztor, Barna and Shenfeld, Idan and Ramponi, Giorgia and Krause, Andreas}, year = {2026}, booktitle = {Conference on Language Modeling (2026)}, } - Majority Voting for Code GenerationWorkshop on Test-Time Updates @ International Conference on Learning Representations (2026)pdfposter
bibtex
@inproceedings{launer2026aligning, title = {Majority Voting for Code Generation}, author = {Launer, Tim and Hübotter, Jonas and Bagatella, Marco and Hakimi, Ido and Krause, Andreas}, year = {2026}, booktitle = {Workshop on Test-Time Updates @ International Conference on Learning Representations (2026)}, } - Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero DataarXiv preprint arXiv:2602.21320pdfwebsitecodethread
bibtex
@article{acikgoz2026tool, title = {Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data}, author = {Can Acikgoz, Emre and Qian, Chen and Hübotter, Jonas and Ji, Heng and Hakkani-Tür, Dilek and Tur, Gokhan}, year = {2026}, journal = {arXiv preprint arXiv:2602.21320}, } - Reinforcement Learning via Self-DistillationInternational Conference on Machine Learning (2026)Best Paper Award at ICLR 2026 Workshop on Test-Time Updates and Oral Presentation at ICLR 2026 Workshop on Scaling Post-training for LLMs.pdfwebsitecodeposterthread
bibtex
@inproceedings{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}, booktitle = {International Conference on Machine Learning (2026)}, } - Self-Distillation Enables Continual LearningInternational Conference on Machine Learning (2026)Best Paper Award at ICLR 2026 Workshop on Lifelong Agents.
- Test-time Offline Reinforcement Learning on Goal-related ExperienceInternational Conference on Machine Learning (2026)pdfcode
bibtex
@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 = {2026}, booktitle = {International Conference on Machine Learning (2026)}, }
2025
- Learning on the Job: Test-Time Curricula for Targeted Reinforcement LearningarXiv preprint arXiv:2510.04786pdfcodemodelsdata
bibtex
@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}, } - Specialization after Generalization: Towards Understanding Test-Time Training in Foundation ModelsInternational Conference on Learning Representations (2026)Oral Presentation at NeurIPS 2025 Workshop on Continual and Compatible Foundation Model Updates.pdfcodemodelsposter
bibtex
@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)}, } - Maximizing Prefix-Confidence at Test-Time Efficiently Improves Mathematical ReasoningWorkshop on Test-Time Scaling and Reasoning Models @ Conference on Language Modeling (2025)pdfposter
bibtex
@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)}, } - DISCOVER: Automated Curricula for Sparse-Reward Reinforcement LearningAdvances in Neural Information Processing Systems (2025)pdfcodeposter
bibtex
@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)}, } - Local Mixtures of Experts: Essentially Free Test-Time Training via Model MergingConference on Language Modeling (2025)pdfcodemodelsposter
bibtex
@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)}, } - Probabilistic Artificial IntelligencearXiv preprint arXiv:2502.05244pdf
bibtex
@article{krause2025probabilistic, title = {Probabilistic Artificial Intelligence}, author = {Krause, Andreas and Hübotter, Jonas}, year = {2025}, journal = {arXiv preprint arXiv:2502.05244}, } - LITE: Efficiently Estimating Gaussian Probability of MaximalityInternational Conference on Artificial Intelligence and Statistics (2025)pdfcodeposter
bibtex
@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
- Active Fine-Tuning of Multi-Task PoliciesInternational Conference on Machine Learning (2025)
- Efficiently Learning at Test-Time: Active Fine-Tuning of LLMsInternational Conference on Learning Representations (2025)Best Paper Award at NeurIPS 2024 Workshop on Fine-Tuning in Modern Machine Learning.pdfcodeposterslides
bibtex
@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)}, } - Transductive Active Learning: Theory and ApplicationsAdvances in Neural Information Processing Systems (2024)Oral Presentation at ICML 2024 Workshop on Aligning Reinforcement Learning Experimentalists and Theorists.pdfcodeposterslides
bibtex
@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
- Efficient Exploration in Continuous-time Model-based Reinforcement LearningAdvances in Neural Information Processing Systems (2023)pdf
bibtex
@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)}, } - Tuning Legged Locomotion Controllers via Safe Bayesian OptimizationConference on Robot Learning (2023)pdfcodevideo
bibtex
@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
- A Cut-Matching Game for Constant-Hop ExpandersACM-SIAM Symposium on Discrete Algorithms (2025)pdf
bibtex
@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)}, }