Explainers
No explainer here yet. This is the kind of cell that gets one as soon as something in the queue earns it.
Unread — 2
paper · Jun 2020
Liquid Time-constant Networks
The original MIT paper: continuous-time RNNs whose dynamics adapt after training — the canonical entry to the whole LNN / Liquid AI lineage.
arXiv 2006.04439 post · Sep 2024From Liquid Neural Networks to Liquid Foundation Models
Traces the lineage from Hasani’s MIT liquid networks to Liquid AI’s production LFMs — theory becoming a deployable, edge-efficient alternative to transformers.
Liquid AI Research