1 citations · 1 across the 6 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
MetaLearnNCA: Few-Shot Offline Meta-Learning via Interacting Neural Cellular Automata
Etienne Guichard, Stefano Nichele
Few-shot meta-learning traditionally formulates task adaptation either as analytical gradient descent through unrolled computational graphs or as metric-based distance comparisons…
cs.LG2026
Neural Cellular Automata Learn General Features in their Hidden Channels
Etienne Guichard, Stefano Nichele
Modern deep learning models achieve impressive generalization through over-parameterization, but this paradigm often struggles with overfitting and memorization in few-shot regimes…