A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
Proposes a retraining-free model quantization method using one-shot weight-coupling learning to achieve efficient compression without fine-tuning.
Unknown
This paper identifies and addresses suboptimal fine-tuning in LoRA for wide models by proposing Lora+, a method that improves parameter efficiency and performance.
Unknown
Gora introduces gradient-driven adaptive low-rank adaptation that matches full fine-tuning performance.
Unknown
This paper analyzes the expressive power of Low-Rank Adaptation (LoRA) for fine-tuning pre-trained models.
Unknown
LoRA freezes pre-trained model weights and injects trainable low-rank matrices to enable efficient fine-tuning of large language models.
Baohao Liao, Yan Meng, C. Monz
This paper proposes a parameter-efficient fine-tuning method that matches full fine-tuning performance without introducing additional inference latency.
Unknown
FourierFT is a parameter-efficient fine-tuning method that learns weight updates in the frequency domain via discrete Fourier transform.
Unknown
A survey and benchmark of parameter-efficient fine-tuning methods for pre-trained vision models.
Unknown
This survey provides a comprehensive overview of parameter-efficient fine-tuning (PEFT) methodologies for large language models, addressing the computational challenges of full fine-tuning.
Unknown
Parameter-efficient fine-tuning (PEFT) achieves better performance and lower cost than in-context learning for few-shot tasks.
Unknown
This paper critically reviews and assesses parameter-efficient fine-tuning methods for pretrained language models, highlighting their ability to reduce parameters and memory while maintaining performance.
Ning Ding, Yujia Qin, Guang Yang, et al.
This paper surveys parameter-efficient fine-tuning methods for large pre-trained language models, categorizing approaches and analyzing their trade-offs.