TailLoR applies low-rank updates to the singular value matrix of pre-trained weights while using a soft spectral penalty to protect dominant singular directions during continual learning.
ELLA : Efficient Lifelong Learning for Adapters in Large Language Models
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
-
TailLoR: Protecting Principal Components in Parameter-Efficient Continual Learning
TailLoR applies low-rank updates to the singular value matrix of pre-trained weights while using a soft spectral penalty to protect dominant singular directions during continual learning.