Commit History
25 days ago
-
Update README.md
Verified signaturecb669f4 -
Update README.md
Verified signatureaa2b4a9 -
init: readme
Verified signature# BiMU: Active Continual Learning with Metaplastic Binary Bayesian Neural Networks **ICML 2026** · [Paper (arXiv:2605.30198)](https://arxiv.org/abs/2605.30198) · [OpenReview](https://openreview.net/forum?id=SPZd0HVyiS) · [Code](https://github.com/kellian-cottart/active-continual-learning-bayesianbinn) · [Project page](https://kellian-cottart.github.io/publication/2026-bimu) Kellian Cottart, Théo Ballet, Djohan Bonnet, Damien Querlioz (Université Paris-Saclay, CNRS, C2N) BiMU (Binary Metaplasticity from Uncertainty) is a Bayesian continual-learning rule for binary neural networks: each one-bit weight keeps a probability of being +1 or −1, and its own uncertainty sets how far it may move, so the network keeps learning on long non-stationary streams without replay or task boundaries, and uses the same uncertainty to decide which samples are worth labelling. ## Model details | | …e04de3f -
initial commit
Verified signatured43b386