Djohan Bonnet — accepted AI-conference papers

2026

Active Continual Learning with Metaplastic Binary Bayesian Neural Networks

Kellian Cottart, Theo Ballet, Djohan Bonnet, Damien Querlioz

ICML 2026poster

Always-on edge systems must keep learning as conditions change under tight compute budgets and must detect unreliable predictions. Bayesian binary neural networks are attractive in this setting, but mean-field Bernoulli posteriors can saturate on long non-stationary streams, wiping out epistemic unc…

Cited by 0 Source ↗Scholar ↗

2026

Learning to Remember, Learn, and Forget in Attention-Based Models

Djohan Bonnet, Jamie Lohoff, Jan Finkbeiner, Elidona Shiqerukaj, Emre Neftci

ICML 2026poster

In-Context Learning (ICL) in transformers acts as an online associative memory and is believed to underpin their high performance on complex sequence processing tasks. However, in gated linear attention models, this memory has a fixed capacity and is prone to interference, especially for long sequen…

Cited by 1 Source ↗Scholar ↗