Abstract We propose Conditional Adapter (CoDA), a parameter-efficient transfer learning
method that also improves inference efficiency. CoDA generalizes beyond standard adapter …

Deep learning algorithms are increasingly employed at the edge. However, edge devices
are resource constrained and thus require efficient deployment of deep neural networks …

Sparse neural networks are a key factor in developing resource-efficient machine learning
applications. We propose the novel and powerful sparse learning method Adaptive …

In previous research, the prevailing assumption was that Graph Neural Networks (GNNs)
precisely depicted the interconnections among nodes within the graph's architecture …

Post-training Sparsity (PTS) is a recently emerged avenue that chases efficient network
sparsity with limited data in need. Existing PTS methods however undergo significant …

Following their success in natural language processing (NLP), there has been a shift
towards transformer models in computer vision. While transformers perform well and offer …

Recent research has focused on weight sparsity in neural network training to reduce FLOPs,
aiming for improved efficiency (test accuracy wrt training FLOPs). However, sparse weight …

Compact representation of multimedia signals using implicit neural representations (INRs)
has advanced significantly over the past few years, and recent works address their …

Large language models (LLMs) have made significant strides in complex tasks, yet their
widespread adoption is impeded by substantial computational demands. With hundreds of …

Recent works have explored the use of weight sparsity to improve the training efficiency (test
accuracy wrt training FLOPs) of deep neural networks (DNNs). These works aim to reduce …