UnIT enables unstructured, input-aware pruning of individual MACs on MCUs without retraining, reporting up to 82% MAC reduction and up to 84% energy savings at 0.48 to 7% accuracy loss.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
UnIT: Scalable Unstructured Inference-Time Pruning for MAC-efficient Neural Inference on MCUs
UnIT enables unstructured, input-aware pruning of individual MACs on MCUs without retraining, reporting up to 82% MAC reduction and up to 84% energy savings at 0.48 to 7% accuracy loss.