π§΅Excited to present our latest work at #Neurips25! Together with @avm.bsky.social, we discover ππ‘ππ§π§ππ₯π¬ ππ¨ π’π§ππ’π§π’ππ²: regions in neural networks loss landscapes where parameters diverge to infinity (in regression settings!)
We find that MLPs in these channels can take derivatives and compute GLUs π€―
