Banner Banner
Icon

July 11, 2025

ICML 2025 Conference Contributions

DAMS, DEEM, ML and MLsec at ICML 2025

Various BIFOLD researchers contribute to the 42nd International Conference on Machine Learning (ICML 2025), to be held from July 13 to July 19, 2025, in Vancouver, Canada. The presented work addresses challenges at the intersection of machine learning security, computational biology, and cross-modal data quality.

ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics.

Below is an overview of BIFOLD’s contributions:

  • Adversarial Inputs for Linear Algebra Backends. Jonas Möller, Lukas Pirch, Felix Weissberg, Sebastian Baunsgaard, Thorsten Eisenhofer, Konrad Rieck.
  • [PDF] [Code]
  • scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell Data. Olga Ovcharenko, Florian Barkmann, Philip Toma, Imant Daunhawer, Julia E. Vogt, Sebastian Schelter, Valentina Boeva.
  • The paper has been selected as a spotlight poster
  • [PDF] [Code]
  • Objective drives the consistency of representational similarity across datasets. Laure Ciernik, Lorenz Linhardt, Marco Morik, Jonas Dippel, Simon Kornblith, Lukas Muttenthaler.
  • [PDF] [Code]

  • Workshop: Unifying Data Curation Frameworks Across Domains (DataWorld)
  • Towards Cross-Modal Error Detection with Tables and Images. Olga Ovcharenko, Sebastian Schelter.
  • [PDF] [Code]