Diffusion models are powerful, but they require a lot of time and data to train. We propose
Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training …

The rapid growth of Large Language Models (LLMs) has been a driving force in
transforming various domains, reshaping the artificial general intelligence landscape …

Current techniques for deep neural network (DNN) pruning often involve intricate multi-step
processes that require domain-specific expertise making their widespread adoption …

Pruning at initialization (PaI) aims to remove weights of neural networks before training in
pursuit of training efficiency besides the inference. While off-the-shelf PaI methods manage …

Large Language Models (LLMs) have transformed the landscape of artificial intelligence,
while their enormous size presents significant challenges in terms of computational costs …

Densely structured pruning methods utilizing simple pruning heuristics can deliver
immediate compression and acceleration benefits with acceptable benign performances …

Sparsification-based pruning has been an important category in model compression.
Existing methods commonly set sparsity-inducing penalty terms to suppress the importance …

Structured pruning reduces the computational overhead of deep neural networks by
removing redundant sub-structures. However, assessing the relative importance of different …

Deep neural networks (DNNs) have been a pivotal technology in a myriad of fields, boasting
remarkable achievements. Nevertheless, their substantial workload and inherent …

With the rapid development of artificial intelligence and Unmanned Aerial Vehicle (UAV)
technology, AI-based UAVs are increasingly utilized in various industrial and civilian …