HiP-LoRA decomposes LoRA updates into principal and residual spectral channels with a singular-value-weighted stability budget to reduce forgetting and interference during foundation model adaptation.
Orthogonal subspace learning for lan- guage model continual learning
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
-
HiP-LoRA: Budgeted Spectral Plasticity for Robust Low-Rank Adaptation
HiP-LoRA decomposes LoRA updates into principal and residual spectral channels with a singular-value-weighted stability budget to reduce forgetting and interference during foundation model adaptation.