Jonas Hübotter

Doctoral Researcher at ETH Zurich. I work on Local Learning and Active Fine-Tuning.

prof_pic.png

I am a doctoral researcher in the Learning and Adaptive Systems Group at ETH Zurich working with Andreas Krause. 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. As an intern at Citadel Securities, I have previously worked with Guillaume Basse and Sören Künzel on time-series prediction. I am a recipient of the ETH Medal.

My research aims to improve the performance of foundation models by utilizing tools from active learning for few-shot learning, active inference, and adaptive computation. Beyond this, I have broad interests including (approximate) probabilistic inference, optimization, and online learning.

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

Contacts:jhuebotter@ethz.ch Google Scholar GitHub Linkedin

Announcements

Oct, 2024 NeurIPS 2024: Our work Transductive Active Learning: Theory and Applications was accepted! We will also present our work on efficiently learning at test-time with LLMs with an oral presentation at the Fine-Tuning in Modern ML workshop.
Jun, 2024 ICML 2024: Our work on Transductive Active Learning with Application to Safe Bayesian Optimization was accepted as an oral presentation (top 5%) at the Aligning RL Experimentalists and Theorists workshop.
Mar, 2024 ICLR 2024: Our work on Active Few-Shot Fine-Tuning was accepted at the Bridging the Gap Between Practice and Theory in Deep Learning workshop!
Feb, 2024 I received the ETH Medal for my Master’s thesis on transductive active learning 🎉! Big thanks to my incredible collaborators Bhavya Sukhija, Lenart Treven, Yarden As, and Andreas Krause.

Selected Publications

  1. Oral
    Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
    Jonas Hübotter, Sascha Bongni, Ido Hakimi , and 1 more author
    arXiv preprint arXiv:2410.08020, 2024
    Oral Presentation at NeurIPS Workshop on Fine-Tuning in Modern Machine Learning, 2024.
  2. NeurIPS 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.

Talks

  • Efficiently Learning at Test-Time with LLMs via Transductive Active Learning
    Invited Talk, Trillion Parameter Consortium (TPC) Seminar Series, 5 Mar 2025.
  • Efficiently Learning at Test-Time: Active Fine-Tuning of LLMsrecording, slides
    Contributed Talk, NeurIPS Workshop on Fine-Tuning in Modern Machine Learning, Vancouver, 14 Dec 2024.
  • Interview with Machine Learning Street Talk (MLST) podcast, Nov 2024.
  • Transductive Active Learning for Fine-Tuning Large (Language) Modelsslides
    Invited Talk, Machine Learning and Modelling Seminar, Czech Academy of Sciences, Prague, 21 Nov 2024.
  • Efficiently Learning at Test-Time with LLMsrecording, slides
    Invited Talk, Zurich AI Meetup, Zurich, 3 Dec 2024.
    Invited Talk, Tufa Labs AI Meetup, Zurich, 29 Oct 2024.
  • Transductive Active Learning with Application to Safe Bayesian Optimizationrecording, slides
    Contributed Talk, ICML Workshop on Aligning Reinforcement Learning Experimentalists and Theorists, Vienna, 26 Jul 2024.
  • Active Fine-Tuning of Large Neural Networksslides
    Contributed Talk, Machine Learning Seminar, ETH Zurich, 18 Apr 2024.

Supervision

I have had the privilege of advising several BSc and MSc students during their theses and semester projects.

  • Nicolas Menet: Efficiently Estimating Gaussian Probability of Maximality (with Parnian Kassraie)
  • Sascha Bongni: Active Fine-Tuning of Large Language Models
  • Pablo Lahmann: Safe Control as Inference (with Yarden As)
  • Anh Duc Nguyen: Safe Bayesian Optimization without Regret
You can find a list of potential projects here. If you are interested in working with me, please reach out.