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.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages =
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.