Dynamic neural network is an emerging research topic in deep learning. Compared to static
models which have fixed computational graphs and parameters at the inference stage …

Deep neural networks (DNNs) typically have a single exit point that makes predictions by
running the entire stack of neural layers. Since not all inputs require the same amount of …

Federated learning (FL) suffers from data heterogeneity, where the diverse data distributions
across clients make it challenging to train a single global model effectively. Existing …

Most state-of-the-art deep neural networks use static inference graphs, which makes it
impossible for such networks to dynamically adjust the depth or width of the network …

This paper introduces TinySaver, an early-exit-like dynamic model compression approach
which employs tiny models to substitute large models adaptively. Distinct from traditional …

Generative DNNs are a powerful tool for image synthesis, but they are limited by their
computational load. On the other hand, given a trained model and a task, eg faces …

Leveraging recent advancements in large language models, modern neural code
completion models have demonstrated the capability to generate highly accurate code …

Abstract Dynamic Neural Networks (DNNs) are an evolving research field within deep
learning (DL), offering a robust, adaptable, and efficient alternative to the conventional Static …

Edge devices provide inference on predictive tasks to many end-users. However, deploying
deep neural networks that achieve state-of-the-art accuracy on these devices is infeasible …

In the vanilla federated learning (FL) framework, the central server distributes a globally
unified model to each client and uses labeled samples for training. However, in most cases …