DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models
Large Language Models (LLMs) have achieved remarkable success in various natural
language processing tasks, including language modeling, understanding, and generation …
language processing tasks, including language modeling, understanding, and generation …
SNP: Structured Neuron-level Pruning to Preserve Attention Scores
Multi-head self-attention (MSA) is a key component of Vision Transformers (ViTs), which
have achieved great success in various vision tasks. However, their high computational cost …
have achieved great success in various vision tasks. However, their high computational cost …
Weed Recognition at Soybean Seedling Stage Based on YOLOV8nGP+ NExG Algorithm
T Sun, L Cui, L Zong, S Zhang, Y Jiao, X Xue, Y Jin - Agronomy, 2024 - mdpi.com
The high cost of manual weed control and the overuse of herbicides restrict the yield and
quality of soybean. Intelligent mechanical weeding and precise application of pesticides can …
quality of soybean. Intelligent mechanical weeding and precise application of pesticides can …
A Lightweight SAR Ship Detection Network Based on Deep Multi-scale Grouped Convolution, Network Pruning and Knowledge Distillation
B Hu, H Miao - IEEE Journal of Selected Topics in Applied …, 2024 - ieeexplore.ieee.org
Deep learning has proven to be highly effective in synthetic aperture radar (SAR) image
target detection. However, many latest deep learning models have predominantly focused …
target detection. However, many latest deep learning models have predominantly focused …
A novel iteration scheme with conjugate gradient for faster pruning on transformer models
J Li, Y Zhu, K Sun - Complex & Intelligent Systems, 2024 - Springer
Pre-trained models based on the Transformer architecture have significantly advanced
research within the domain of Natural Language Processing (NLP) due to their superior …
research within the domain of Natural Language Processing (NLP) due to their superior …