CATS enables collaborative transformer inference on up to 16 ultra-low-power wireless devices, supporting models up to 14 times larger than a single device can run via SomeGather pruning and message-dropout robustness.
Communication-efficient multi-device in- ference acceleration for transformer models.arXiv preprint arXiv:2505.19342,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Going Beyond the Edge: Distributed Inference of Transformer Models on Ultra-Low-Power Wireless Devices
CATS enables collaborative transformer inference on up to 16 ultra-low-power wireless devices, supporting models up to 14 times larger than a single device can run via SomeGather pruning and message-dropout robustness.