Speaker: Jenia Jitsev, Jülich Supercompting Center/LAION e.V.
Date: 26.01.2026, 11:00 am
Title: Open Foundation Models: Reproducible Science of Strongly Scalable Transferable Learning
Abstract:
In this lecture, we explain how scaling laws can be used to predict the performance of foundation models and to systematically compare different learning methods. We show that broad, generalist pre-training is key to robust generalization and effective transfer across tasks and domains, and how scaling laws make it possible to draw reliable conclusions about large-scale models from small-scale experiments.
A second focus of the lecture is the importance of open foundation models, where data, training procedures, and evaluation are fully transparent—an essential prerequisite for reliable scaling-law studies and the collaborative development of new learning methods. We also discuss why established benchmarks often fail to capture major weaknesses of modern models and present new evaluation techniques based on controlled variations of simple tasks that make generalization failures clearly visible.
Jenia Jitsev
Jenia Jitsev is co-founder and scientific lead of LAION e.V, a non-profit research organization committed to research on open large-scale foundation models and datasets. He also leads Scalable Learning & Multi-Purpose AI (SLAMPAI) lab at Juelich Supercomputer Center and is a member of ELLIS
