MOONSHOT is a wrapper framework that combines reconstruction loss and Taylor approximation objectives to improve one-shot pruning results on LLMs and vision models.
Namhoon Lee, Thalaiyasingam Ajanthan, Stephen Gould, and Philip H
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MOONSHOT : A Framework for Multi-Objective Pruning of Vision and Large Language Models
MOONSHOT is a wrapper framework that combines reconstruction loss and Taylor approximation objectives to improve one-shot pruning results on LLMs and vision models.