A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
RidgeloRA enhances LoRA by incorporating matrix ridge regression to improve parameter-efficient fine-tuning of large language models.
Unknown
This paper proposes parameter-efficient fine-tuning methods for protein language models to democratize their application, reducing computational costs while maintaining performance.
Unknown
Introduces Correlated Low-Rank Adaptation (CoLoRA), a novel framework that explicitly models correlations among low-rank factors to improve parameter-efficient fine-tuning of convolutional networks.
Unknown
This paper proposes parameter-efficient fine-tuning (PEFT) methods for geospatial foundation models, enabling effective adaptation with minimal parameter updates.
Unknown
DiffFit proposes a simple parameter-efficient fine-tuning strategy for large diffusion models, enabling transferability with minimal trainable parameters.
Unknown
This paper introduces SCT, a simple yet effective parameter-efficient fine-tuning method for vision transformers that selectively updates salient channels based on feature map statistics.
Unknown
Proposes a flexible, parameter-efficient fine-tuning scheme for pretrained architectures to improve generalization across tasks.
Unknown
This paper provides a comprehensive analysis of parameter-efficient fine-tuning methods across diverse applications including reasoning, video description, and more.
Unknown
ADAPTERX is a general parameter-efficient fine-tuning framework where different blocks recursively select the most suitable adapters for vision tasks.
Dan Zhang, Tao Feng, Lilong Xue, et al.
This survey provides a comprehensive overview of Parameter-Efficient Fine-Tuning (PEFT) methods for foundation models, categorizing and analyzing approaches to reduce computational costs while maintaining performance.
Unknown
LongLoRA enables efficient context extension for large language models via sparse local attention and parameter-efficient fine-tuning.
Unknown
DyLoRA introduces a dynamic, search-free low-rank adaptation method that trains LoRA blocks for a range of ranks to improve parameter-efficient tuning of pre-trained models.