A pruning method that iteratively generates both layer-pruned and filter-pruned candidates, keeps the one with the highest CKA similarity to the parent, and achieves high FLOPs reduction on small ResNets.
LLMCarbon: Modeling the end-to-end carbon footprint of large language models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pruning Everything, Everywhere, All at Once
A pruning method that iteratively generates both layer-pruned and filter-pruned candidates, keeps the one with the highest CKA similarity to the parent, and achieves high FLOPs reduction on small ResNets.