WARD: Runtime Workload-Adaptive Vision TRansformer Framework for Dependable Edge AI
WARD is presented, a runtime-adaptive Vision Transformer framework that combines channel-wise subnetwork partitioning, reliability-aware continual learning, and dynamic operating-mode scheduling to jointly optimize performance, fault tolerance, and adaptation according to runtime conditions.
Mahdi Taheri, Pramit Kumar Bhaduri, MohammadReza Masoumi et al.
· 0 citations