REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
M i L o RA : Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
VLA-GSE uses spectral decomposition of the VLA backbone to create generalized and specialized experts, enabling effective robot task adaptation while updating only 2.51% of parameters and achieving 81.2% zero-shot success on LIBERO-Plus.
GIFT guides adapter fine-tuning on base models with confidence signals from instruction-tuned models before merging, yielding task-specialized models that outperform direct fine-tuning on math and knowledge benchmarks.
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.
Fisher information from the target data distribution supplies a task-dependent criterion for selecting LoRA directions that outperforms weight-magnitude heuristics.
citing papers explorer
-
Representation-Guided Parameter-Efficient LLM Unlearning
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
-
VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts
VLA-GSE uses spectral decomposition of the VLA backbone to create generalized and specialized experts, enabling effective robot task adaptation while updating only 2.51% of parameters and achieving 81.2% zero-shot success on LIBERO-Plus.
-
GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
GIFT guides adapter fine-tuning on base models with confidence signals from instruction-tuned models before merging, yielding task-specialized models that outperform direct fine-tuning on math and knowledge benchmarks.
-
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.
-
Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning
Fisher information from the target data distribution supplies a task-dependent criterion for selecting LoRA directions that outperforms weight-magnitude heuristics.