7 papers
ORXE: Orchestrating Experts for Dynamically Configurable Efficiency
Qingyuan Wang, Guoxin Wang, Barry Cardiff +1
This paper presents ORXE, a modular and adaptable framework for achieving real-time configurable efficiency in AI models. By leveraging a collection of pre-trained experts with div…
DyCE: Dynamically Configurable Exiting for Deep Learning Compression and Real-time Scaling
Qingyuan Wang, Barry Cardiff, Antoine Frappé +2
Conventional deep learning (DL) model compression and scaling methods focus on altering the model's components, impacting the results across all samples uniformly. However, since s…
NOMA-Based Cooperative Relaying with Receive Diversity in Nakagami-m Fading Channels
Vaibhav Kumar, Barry Cardiff, Mark F Flanagan
Non-orthogonal multiple access (NOMA) is being widely considered as a potential candidate to enhance the spectrum utilization in beyond fifth-generation (B5G) communications. In th…
Delay Violation Probability and Effective Rate of Downlink NOMA over - Fading Channels
Vaibhav Kumar, Barry Cardiff, Shankar Prakriya +1
Non-orthogonal multiple access (NOMA) is a potential candidate to further enhance the spectrum utilization efficiency in beyond fifth-generation (B5G) standards. However, there has…
DCentNet: Decentralized Multistage Biomedical Signal Classification using Early Exits
Xiaolin Li, Binhua Huang, Barry Cardiff +1
DCentNet is a novel decentralized multistage signal classification approach designed for biomedical data from IoT wearable sensors, integrating early exit points (EEP) to enhance e…
Tiny Models are the Computational Saver for Large Models
Qingyuan Wang, Barry Cardiff, Antoine Frappé +2
This paper introduces TinySaver, an early-exit-like dynamic model compression approach which employs tiny models to substitute large models adaptively. Distinct from traditional co…