HyperAdapter performs PEFT of ViTs via soft hypergraph construction, hyperedge-level bottleneck adaptation, and incidence-based diffusion, claiming consistent gains over token-wise adapters on structured visual benchmarks.
Parameter-efficient orthogonal finetuning via butterfly factorization
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
DoRA improves LoRA by decomposing weights into magnitude and direction and updating only direction with low-rank matrices, closing much of the gap to full fine-tuning.
An overview revisits LoRA variants by categorizing advances in architectural design, efficient optimization, and applications while linking them to classical signal processing tools for principled fine-tuning.
citing papers explorer
-
Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers
HyperAdapter performs PEFT of ViTs via soft hypergraph construction, hyperedge-level bottleneck adaptation, and incidence-based diffusion, claiming consistent gains over token-wise adapters on structured visual benchmarks.
-
DoRA: Weight-Decomposed Low-Rank Adaptation
DoRA improves LoRA by decomposing weights into magnitude and direction and updating only direction with low-rank matrices, closing much of the gap to full fine-tuning.
-
Low-Rank Adaptation Redux for Large Models
An overview revisits LoRA variants by categorizing advances in architectural design, efficient optimization, and applications while linking them to classical signal processing tools for principled fine-tuning.