LARS constrains activation subspaces to decouple memory use from sequence length, cutting GPU memory by 33.5% and CPU memory by 52% versus LoRA while keeping accuracy comparable.
Sequence Length Ceiling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Parameter Efficiency Is Not Memory Efficiency: Rethinking Fine-Tuning for On-Device LLM Adaptation
LARS constrains activation subspaces to decouple memory use from sequence length, cutting GPU memory by 33.5% and CPU memory by 52% versus LoRA while keeping accuracy comparable.