An ICA-based structured pruning method that preserves functional neuron networks shows mixed performance against FLAP, with overclaimed state-of-the-art results.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Pruning Large Language Models by Identifying and Preserving Functional Networks
An ICA-based structured pruning method that preserves functional neuron networks shows mixed performance against FLAP, with overclaimed state-of-the-art results.