bethgelab/frequency_determines_performance
Updated
•
2
Bethgelab
university
AI & ML interests
Foundation Models, Scaling Laws, Continual Pretraining, Data-centric ML, Neuroscience, Human-Machine comparisons
Organization Card
About org cards
The official huggingface organisation for the Bethgelab, University of Tuebingen. We are an interdisciplinary group working on two broad themes:
- Foundation Models: scaling laws, continual pretraining, lifelong benchmarking and data-centric perspectives on (compositional) generalisation.
- Neuroscience: neural system identification, gaze prediction, object-centric motion perception, brain-inspired AI, human-machine comparisons
models
None public yet