Publications

2026

• ICML
  Intrinsic Credit Assignment for Long Horizon Interaction

  Ilze Amanda Auzina*, Joschka Strüber*, Sergio Hernández-Gutiérrez*, Shashwat Goel, Ameya Prabhu, Matthias Bethge

  International Conference on Machine Learning (ICML), 2026

  Bib arXiv Website Code

  @inproceedings{auzina2026intrinsic,
    title={Intrinsic Credit Assignment for Long Horizon Interaction},
    author={Auzina, Ilze Amanda and Str{\"u}ber, Joschka and Hern{\'a}ndez-Guti{\'e}rrez, Sergio and Goel, Shashwat and Prabhu, Ameya and Bethge, Matthias},
    booktitle={Proceedings of the 43rd International Conference on Machine Learning},
    year={2026}
  }

• ICML-W
  RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments

  Babak Rahmani*, Sebastian Dziadzio*, Joschka Strüber*, Sergio Hernández-Gutiérrez, Matthias Bethge

  ICML 2026 Workshop on Agents in the Wild: Safety, Security, and Beyond (AIWILD)

  Bib

  @inproceedings{rahmani2026revengebench,
    title={RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments},
    author={Rahmani, Babak and Dziadzio, Sebastian and Str{\"u}ber, Joschka and Hern{\'a}ndez-Guti{\'e}rrez, Sergio and Bethge, Matthias},
    booktitle={ICML 2026 Workshop on Agents in the Wild: Safety, Security, and Beyond (AIWILD)},
    year={2026}
  }

• ICML-W
  QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents

  Sergio Hernández-Gutiérrez, Matteo Merler, Ilze Amanda Auzina, Joschka Strüber, Ameya Prabhu, Matthias Bethge

  ICML 2026 Workshop on Reinforcement Learning from World Feedback (RLxF)

  Bib arXiv

  @inproceedings{hernandezgutierrez2026qval,
    title={QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents},
    author={Hern{\'a}ndez-Guti{\'e}rrez, Sergio and Merler, Matteo and Auzina, Ilze Amanda and Str{\"u}ber, Joschka and Prabhu, Ameya and Bethge, Matthias},
    booktitle={ICML 2026 Workshop on Reinforcement Learning from World Feedback (RLxF)},
    year={2026}
  }

• arXiv
  DataComp-VLM: Improved Open Datasets for Vision-Language Models

  Matteo Farina*, Vishaal Udandarao*, Thao Nguyen*, Selim Kuzucu, Maximilian Böther, Andreas Hochlehnert, Adhiraj Ghosh, Marianna Nezhurina, Karsten Roth, Joschka Strüber, Yuhui Zhang, Sebastian Dziadzio, Elaine Sui, Soumya Jahagirdar, Dhruba Ghosh, Hasan Hammoud, Thomas De Min, Simone Caldarella, Jehanzeb Mirza, Sedrick Keh, Mehdi Cherti, Hilde Kuehne, Bernt Schiele, Serena Yeung-Levy, Muhammad Ferjad Naeem, Federico Tombari, Ana Klimovic, Elisa Ricci, Matthias Bethge, Sewoong Oh, Ameya Prabhu, Alessio Tonioni, Jenia Jitsev, Massimiliano Mancini, Ludwig Schmidt, Nikhil Parthasarathy

  arXiv Preprint

  Bib arXiv

  @misc{farina2026datacompvlm,
    title={DataComp-VLM: Improved Open Datasets for Vision-Language Models},
    author={Farina, Matteo and Udandarao, Vishaal and Nguyen, Thao and Kuzucu, Selim and B{\"o}ther, Maximilian and Hochlehnert, Andreas and Ghosh, Adhiraj and Nezhurina, Marianna and Roth, Karsten and Str{\"u}ber, Joschka and Zhang, Yuhui and Dziadzio, Sebastian and Sui, Elaine and Jahagirdar, Soumya and Ghosh, Dhruba and Hammoud, Hasan and De Min, Thomas and Caldarella, Simone and Mirza, Jehanzeb and Keh, Sedrick and Cherti, Mehdi and Kuehne, Hilde and Schiele, Bernt and Yeung-Levy, Serena and Naeem, Muhammad Ferjad and Tombari, Federico and Klimovic, Ana and Ricci, Elisa and Bethge, Matthias and Oh, Sewoong and Prabhu, Ameya and Tonioni, Alessio and Jitsev, Jenia and Mancini, Massimiliano and Schmidt, Ludwig and Parthasarathy, Nikhil},
    year={2026},
    eprint={2606.28551},
    archivePrefix={arXiv},
    primaryClass={cs.CV},
    url={https://arxiv.org/abs/2606.28551}
  }

2025

• ICML-W Oral
  Measuring Belief Updates in Curious Agents

  Joschka Strüber*, Ilze Amanda Auzina*, Shashwat Goel, Susanne Keller, Jonas Geiping, Ameya Prabhu, and Matthias Bethge

  ICML 2025 Workshop on Assessing World Models

  Bib PDF

  @inproceedings{strueber2025measuring,
    title={Measuring Belief Updates in Curious Agents},
    author={Str{\"u}ber, Joschka and Auzina, Ilze Amanda and Goel, Shashwat and Keller, Susanne and Geiping, Jonas and Prabhu, Ameya and Bethge, Matthias},
    booktitle={ICML 2025 Workshop on Assessing World Models},
    year={2025}
  }

• ICML Spotlight
  Great Models Think Alike and this Undermines AI Oversight

  Shashwat Goel*, Joschka Strüber*, Ilze Amanda Auzina*, Karuna K Chandra, Ponnurangam Kumaraguru, Douwe Kiela, Ameya Prabhu, Matthias Bethge, and Jonas Geiping

  International Conference on Machine Learning (ICML), 2025

  Bib arXiv Website Code Data

  @inproceedings{goel2025great,
    title={Great Models Think Alike and this Undermines AI Oversight},
    author={Goel, Shashwat and Str{\"u}ber, Joschka and Auzina, Ilze Amanda and Chandra, Karuna K and Kumaraguru, Ponnurangam and Kiela, Douwe and Prabhu, Ameya and Bethge, Matthias and Geiping, Jonas},
    booktitle={Proceedings of the 42nd International Conference on Machine Learning},
    year={2025}
  }