This paper proposes filtering cloud-verification requests by combining token-level uncertainty with attention-based importance, claiming energy savings up to 40.7% in wireless hybrid LLM inference.
Harnessing the power of llms in practice: A survey on chatgpt and beyond,
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.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Energy-Efficient Wireless LLM Inference via Uncertainty and Importance-Aware Speculative Decoding
This paper proposes filtering cloud-verification requests by combining token-level uncertainty with attention-based importance, claiming energy savings up to 40.7% in wireless hybrid LLM inference.