CEBRA was initially developed by Mackenzie Mathis and Steffen Schneider (2021+), who are co-inventors on the patent application WO2023143843. Jin Hwa Lee contributed significantly to our first paper:

Schneider, S., Lee, J.H., & Mathis, M.W. Learnable latent embeddings for joint behavioural and neural analysis. Nature 617, 360–368 (2023)

CEBRA is actively developed by Mackenzie Mathis and Steffen Schneider and their labs.

It is a publicly available tool that has benefited from contributions and suggestions from many individuals: CEBRA/graphs/contributors.

• Steffen Schneider, Rodrigo González Laiz, Markus Frey, Mackenzie W. Mathis Identifiable attribution maps using regularized contrastive learning. NeurIPS 4th Workshop on Self-Supervised Learning: Theory and Practice (2023)

• Steffen Schneider, Rodrigo González Laiz, Anastasiia Filippova, Markus Frey, Mackenzie W. Mathis Time-series attribution maps with regularized contrastive learning. AISTATS (2025).

• Rodrigo González Laiz, Tobias Schmidt, Steffen Schneider**: Self-supervised contrastive learning performs non-linear system identification ICLR (2025). Adds the cebra.dynamics module and introduces improvements to cebra.criterions. For advanced features on dynamics learning, the full reference implementation for the paper is available at https://github.com/dynamical-inference/dcl.