A PPO-plus-diffusion policy adaptively allocates LoRA ranks per layer based on channel SNR and data complexity, improving accuracy by up to 0.69% and cutting transmitted parameters by 12.5% over AdaLoRA.
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
-
AirLLM: Diffusion Policy-based Adaptive LoRA for Remote Fine-Tuning of LLM over the Air
A PPO-plus-diffusion policy adaptively allocates LoRA ranks per layer based on channel SNR and data complexity, improving accuracy by up to 0.69% and cutting transmitted parameters by 12.5% over AdaLoRA.