2 papers
cs.LG2025
Activation Sparsity Opportunities for Compressing General Large Language Models
Nobel Dhar, Bobin Deng, Md Romyull Islam +3
Deploying local AI models, such as Large Language Models (LLMs), to edge devices can substantially enhance devices' independent capabilities, alleviate the server's burden, and low…
cs.CR2025
The Robustness of Spiking Neural Networks in Federated Learning with Compression Against Non-omniscient Byzantine Attacks
Manh V. Nguyen, Liang Zhao, Bobin Deng +1
Spiking Neural Networks (SNNs), which offer exceptional energy efficiency for inference, and Federated Learning (FL), which offers privacy-preserving distributed training, is a ris…