all AI news
Parameter-Efficient Tuning of Large Convolutional Models
March 4, 2024, 5:42 a.m. | Wei Chen, Zichen Miao, Qiang Qiu
cs.LG updates on arXiv.org arxiv.org
Abstract: To address the high computational and parameter complexity associated with fine-tuning large pre-trained models, researchers have developed parameter-efficient methods, where only partial parameters are updated for downstream tasks. However, these works often overlook the distinct properties of convolutional kernels, which still remain essential elements in many large models, such as Stable Diffusion. In this study, we first introduce filter subspace by decomposing convolutional kernels within each network layer over a small set of filter subspace …
abstract arxiv complexity computational cs.cv cs.lg fine-tuning large models parameters pre-trained models researchers tasks type
More from arxiv.org / cs.LG updates on arXiv.org
Sliced Wasserstein with Random-Path Projecting Directions
1 day, 7 hours ago |
arxiv.org
The Un-Kidnappable Robot: Acoustic Localization of Sneaking People
1 day, 7 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York