Disaggregated Inference is the division of AI processing tasks across multiple computing layers, such as cloud, edge, and device. NEC Labs America applies disaggregated inference to reduce latency, improve throughput, and optimize energy consumption. This ensures that large AI models can be used effectively in real-time sensing and communication environments, advancing scalable and distributed AI deployment.

Posts

Dual Privacy Protection for Distributed Fiber Sensing with Disaggregated Inference and Fine-tuning of Memory-Augmented Networks

We propose a memory-augmented model architecture with disaggregated computation infrastructure for fiber sensing event recognition. By leveraging geo-distributed computingresources in optical networks, this approach empowers end-users to customize models while ensuring dual privacy protection.