MetaLearnNCA: Few-Shot Offline Meta-Learning via Interacting Neural Cellular Automata

Excerpt

arXiv:2610.08479v1 Announce Type: new Abstract: Few-shot meta-learning traditionally formulates task adaptation either as analytical gradient descent through unrolled computational graphs or as metric-based distance comparisons over flattened 1D fea- ture vectors, which either incur costly test-time backpropagation or discard native 2D spatial geometry. In this work, we propose METALEARNNCA, a decentralized framework that achieves few-shot adapta- tion through the dynamical interaction of couple