Hystar adapts CLIP-like models to unseen query styles by generating per-input singular-value perturbations with a hypernetwork for attention layers and a new StyleNCE contrastive loss.
One-for-all: Generalized lora for parameter-efficient fine-tuning.arXiv preprint arXiv:2306.07967
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
BID-LoRA uses bi-directional low-rank adapters with retain/new/unlearn pathways and escape unlearning to enable continual learning and unlearning while minimizing knowledge leakage and parameter updates.
Sorting tensor indices enables an adaptive tensorization method that discovers low-rank structure in LLM weights and KV caches, yielding better reconstruction quality than baselines.
Empirical tests show adapters (2-3 per block) and LoRA on deformable attention achieve competitive instance segmentation with 1-6% parameters tuned versus 40-55% for full fine-tuning.
citing papers explorer
-
Hystar: Hypernetwork-driven Style-adaptive Retrieval via Dynamic SVD Modulation
Hystar adapts CLIP-like models to unseen query styles by generating per-input singular-value perturbations with a hypernetwork for attention layers and a new StyleNCE contrastive loss.
-
BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning
BID-LoRA uses bi-directional low-rank adapters with retain/new/unlearn pathways and escape unlearning to enable continual learning and unlearning while minimizing knowledge leakage and parameter updates.
-
EinSort: Sorting is All We Need for Tensorizing LLM
Sorting tensor indices enables an adaptive tensorization method that discovers low-rank structure in LLM weights and KV caches, yielding better reconstruction quality than baselines.
-
Parameter-Efficient Fine-Tuning of Large Pretrained Models for Instance Segmentation Tasks
Empirical tests show adapters (2-3 per block) and LoRA on deformable attention achieve competitive instance segmentation with 1-6% parameters tuned versus 40-55% for full fine-tuning.