420 citations · 2.4k across the 126 of their papers we have counts for
7 papers · 1 filter
QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
Yuhui Xu, Lingxi Xie, Xiaotao Gu +6
Recently years have witnessed a rapid development of large language models (LLMs). Despite the strong ability in many language-understanding tasks, the heavy computational burden l…
Exploring Complicated Search Spaces with Interleaving-Free Sampling
Yunjie Tian, Lingxi Xie, Jiemin Fang +3
The existing neural architecture search algorithms are mostly working on search spaces with short-distance connections. We argue that such designs, though safe and stable, obstacle…
Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks
Xin Chen, Lingxi Xie, Jun Wu +3
Neural architecture search has attracted wide attentions in both academia and industry. To accelerate it, researchers proposed weight-sharing methods which first train a super-netw…
Scalable NAS with Factorizable Architectural Parameters
Lanfei Wang, Lingxi Xie, Tianyi Zhang +2
Neural Architecture Search (NAS) is an emerging topic in machine learning and computer vision. The fundamental ideology of NAS is using an automatic mechanism to replace manual des…
Stabilizing DARTS with Amended Gradient Estimation on Architectural Parameters
Kaifeng Bi, Changping Hu, Lingxi Xie +3
DARTS is a popular algorithm for neural architecture search (NAS). Despite its great advantage in search efficiency, DARTS often suffers weak stability, which reflects in the large…
Data Augmentation Revisited: Rethinking the Distribution Gap between Clean and Augmented Data
Zhuoxun He, Lingxi Xie, Xin Chen +3
Data augmentation has been widely applied as an effective methodology to improve generalization in particular when training deep neural networks. Recently, researchers proposed a f…
Defending Adversarial Attacks by Correcting logits
Yifeng Li, Lingxi Xie, Ya Zhang +3
Generating and eliminating adversarial examples has been an intriguing topic in the field of deep learning. While previous research verified that adversarial attacks are often frag…