Jonas Hübotter

I am a PhD student in the Learning and Adaptive Systems Group at ETH Zurich working with Andreas Krause. My research aims to leverage foundation models for solving hard tasks through specialization and reinforcement learning.

From March 2026 – May 2026 I am a research visitor at Stanford working with Carlos Guestrin. Prior to this, I obtained a Master’s degree in Theoretical Computer Science and Machine Learning from ETH Zurich and a Bachelor’s degree in Computer Science and Mathematics from the Technical University of Munich. I am a recipient of the ETH Medal.

Always feel free to reach out to me with things you find exciting.

Contacts: jhuebotter@ethz.ch Google Scholar GitHub Linkedin

News

Mar, 2026	ICLR 2026 Workshops: We will present our work on self-distillation (1, 2) with oral presentations at the LLA workshop and TTU workshop, and as spotlight at the RSI workshop. We also present majority voting for code generation at the TTU workshop.
Feb, 2026	We release three papers on self-distillation: [1] on self-distillation from demonstrations enabling continual learning, [2] on reinforcement learning via self-distillation, and [3] on online self-distillation from raw user interactions. Read more.
Jan, 2026	ICLR 2026: Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models has been accepted!
Nov, 2025	Gave an invited lecture on test-time training at EPFL. Slides are here.
Sep, 2025	NeurIPS 2025: DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning has been accepted! We will also present our work towards understanding the effectiveness of test-time training in foundation models with an oral presentation at the CCFM workshop.

Selected Publications

Aligning Language Models from User Interactions

Thomas Kleine Buening, Jonas Hübotter, Barna Pásztor , and 3 more authors

arXiv preprint arXiv:2603.12273, 2026

Bib PDF Code Website Thread

@article{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},
  journal = {arXiv preprint arXiv:2603.12273},
}

Oral

Reinforcement Learning via Self-Distillation

Jonas Hübotter, Frederike Lübeck, Lejs Behric , and 8 more authors

arXiv preprint arXiv:2601.20802, 2026

Oral Presentation at ICLR 2026 Workshop on Test-Time Updates.

Bib PDF Code Website Thread

@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},
}

Oral

Self-Distillation Enables Continual Learning

Idan Shenfeld, Mehul Damani, Jonas Hübotter , and 1 more author

arXiv preprint arXiv:2601.19897, 2026

Oral Presentation at ICLR 2026 Workshop on Lifelong Agents.

Bib PDF Code Website Thread

@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},
}

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},
}

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.

Bib PDF Code Models

@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)},
}

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 Poster

@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

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)},
}

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)},
}

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)}, }

Latest Talks

→ all talks

Apr 27, 2026 Contributed Talk	Test-Time Self-Distillation ICLR Workshop on Test-Time Updates, Rio de Janeiro
Mar 26, 2026 Interview	Interview on Self-Distillation with Idan Shenfeld Yacine Mahdid
February-April 2026 Invited Talk	Rethinking Post-Training via Self-Distillation 🎥 📝 ELLIS Sardine Seminars, Amazon AGI, Cohere, Engram, Goodfire, Stanford HAI
Jan 13, 2026 Invited Talk	Test-Time Training Agents for Deep Exploration 🎥 📝 BLISS Speaker Series, Berlin
Dec 7, 2025 Contributed Talk	Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models 🎥 📝 NeurIPS Workshop on Continual and Compatible Foundation Model Updates, San Diego

Supervision

I have had the privilege of advising several BSc and MSc students during their theses and semester projects. Some of these projects have led to publications.

Lejs Behric (MSc): Reinforcement Learning via Self-Distillation
Tim Launer (MSc): Evaluating Training Paradigms and Consensus Mechanisms For Learning To Reason (with Marco Bagatella and Ido Hakimi, TTU@ICLR'26)
Dennis Jüni (MSc): Meta Test-Time Training for Image Classification (with Frederike Lübeck, ICLR'26)
Matthias Otth (MSc): Efficient Fine-Tuning and Test-Time Training of Large Language Models for Reasoning Tasks (with Ido Hakimi, SCALR@COLM'25)
Leander Diaz-Bone (MSc): Directed Goal-Conditioned Reinforcement Learning (with Marco Bagatella, NeurIPS'25)
Ryo Bertolissi (BSc): Test-Time Model Merging for Mixture of Local Experts (with Ido Hakimi, COLM'25)
Nicolas Menet (MSc): Efficiently Estimating Gaussian Probability of Maximality (with Parnian Kassraie, AISTATS'25)
Sascha Bongni (BSc): Active Fine-Tuning of Large Language Models (ICLR'25)
Pablo Lahmann (MSc): Safe Control as Inference (with Yarden As)
Anh Duc Nguyen (BSc): Safe Bayesian Optimization without Regret

You can find a list of potential projects of our research group here. If you want to work with me, please send me an email describing your area of interest. Please also attach your CV and up-to-date transcripts.