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.
Large language models and future of information retrieval: Opportunities and challenges,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2025 1verdicts
CONDITIONAL 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.