Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Rethinking the Rank Threshold for LoRA Fine-Tuning
Juneyoung Park
A recent landscape analysis of LoRA fine-tuning in the neural tangent kernel regime establishes a sufficient condition on the LoRA rank for the absence of spuri…
cs.LG2026
LCSB: Layer-Cyclic Selective Backpropagation for Memory-Efficient On-Device LLM Fine-Tuning
Juneyoung Park, Eunbeen Yoon, Seongwan Kim. Jaeho Lee
Memory-efficient backpropagation (MeBP) has enabled first-order fine-tuning of large language models (LLMs) on mobile devices with less than 1GB memory. However, MeBP requires back…
cs.LG2026
Memory-Efficient Structured Backpropagation for On-Device LLM Fine-Tuning
Juneyoung Park, Yuri Hong, Seongwan Kim +1
On-device fine-tuning enables privacy-preserving personalization of large language models, but mobile devices impose severe memory constraints, typically 6--12GB shared across all…