Skip to content
View jonhue's full-sized avatar

Organizations

@who-wrote-that @tony-lang @lasgroup

Block or report jonhue

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
jonhue/README.md

Hello, I'm Jonas

My research aims to leverage foundation models for solving hard tasks through specialization and reinforcement learning. Beyond this, I have broad interests including (approximate) probabilistic inference, optimization, and online learning.

Feel free to reach out to me through jonas.huebotter@inf.ethz.ch.

Pinned Loading

  1. lasgroup/SDPO lasgroup/SDPO Public

    Reinforcement Learning via Self-Distillation (SDPO)

    Python 683 65

  2. ttc ttc Public

    Test-Time Curricula for Targeted RL

    Python 8

  3. activeft activeft Public

    PyTorch library for Active Fine-Tuning

    Python 97 9

  4. transductive-active-learning transductive-active-learning Public

    Transductive Active Learning with Application to Safe Bayesian Optimization

    Python 11 1

  5. algorithms-lab algorithms-lab Public

    Solutions for the problems posed during the Algorithms Lab of 2021 at ETH Zurich.

    C++ 3 2

  6. acts_as_favoritor acts_as_favoritor Public

    Adds Favorite, Follow, Vote, etc. functionality to ActiveRecord models

    Ruby 345 18