BAF reduces memorization in diffusion LoRAs by filtering spectral channels of the adaptation weights that show weak alignment with the base model's principal subspace.
Intrinsic dimensionality explains the effectiveness of language model fine-tuning
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 3polarities
background 3representative citing papers
Pretraining induces stable leading singular vectors that form a reusable spectral basis inherited by downstream tasks, enabling competitive performance with 0.2% trainable parameters on GLUE.
MoLF routes updates between full fine-tuning and LoRA at the optimizer level to match or exceed the better of the two static methods on SQL, medical QA, and counterfactual tasks while an efficient variant outperforms prior adaptive LoRA by up to 20%.
Diagonal plus Low-Rank (DLoR) neural networks achieve universal approximation for general activations by additive or multiplicative decompositions of full-rank transformations.
SPACE induces sparsity in cross-attention parameters via closed-form iterative updates to erase target concepts more effectively than dense baselines in large diffusion models.
citing papers explorer
-
Filtering Memorization from Parameter-Space in Diffusion Models
BAF reduces memorization in diffusion LoRAs by filtering spectral channels of the adaptation weights that show weak alignment with the base model's principal subspace.
-
Pretraining Induces a Reusable Spectral Basis for Downstream Task Adaptation
Pretraining induces stable leading singular vectors that form a reusable spectral basis inherited by downstream tasks, enabling competitive performance with 0.2% trainable parameters on GLUE.
-
Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation
MoLF routes updates between full fine-tuning and LoRA at the optimizer level to match or exceed the better of the two static methods on SQL, medical QA, and counterfactual tasks while an efficient variant outperforms prior adaptive LoRA by up to 20%.
-
Structural Correspondence and Universal Approximation in Diagonal plus Low-Rank Neural Networks
Diagonal plus Low-Rank (DLoR) neural networks achieve universal approximation for general activations by additive or multiplicative decompositions of full-rank transformations.
-
Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models
SPACE induces sparsity in cross-attention parameters via closed-form iterative updates to erase target concepts more effectively than dense baselines in large diffusion models.