LA-LoRA decouples LoRA matrix updates in DPFL settings to improve robustness to privacy noise, delivering up to 16.83% higher accuracy than prior LoRA variants on Swin-B under strict epsilon=1.
Image matching filtering and refinement by planes and beyond.arXiv preprint arXiv:2411.09484
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models
LA-LoRA decouples LoRA matrix updates in DPFL settings to improve robustness to privacy noise, delivering up to 16.83% higher accuracy than prior LoRA variants on Swin-B under strict epsilon=1.
- IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents