ACME customizes Transformer models through a hierarchical cloud-edge-device loop, reducing uploaded data to 6% of centralized systems and improving accuracy by about 10% on CIFAR-100 and Stanford Cars.
MobileLLM: Optimizing sub-billion parameter language models for on-device use cases,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.DC 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
ACME: Adaptive Customization of Large Models via Distributed Systems
ACME customizes Transformer models through a hierarchical cloud-edge-device loop, reducing uploaded data to 6% of centralized systems and improving accuracy by about 10% on CIFAR-100 and Stanford Cars.