Communication-Efficient Hybrid Language Model via Uncertainty-Aware Opportunistic and Compressed Transmission.

Mix2SFL: Two-Way Mixup for Scalable, Accurate, and Communication-Efficient Split Federated Learning.

Privacy-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMix.

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models.

Differentially Private CutMix for Split Learning with Vision Transformer.

Hiding in the Crowd: Federated Data Augmentation for On-Device Learning.

Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixup.

Federated Knowledge Distillation.

Distilling On-Device Intelligence at the Network Edge.

Multi-hop Federated Private Data Augmentation with Sample Compression.

Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data.