5 accepted papers
Speculative decoding can significantly accelerate LLM inference, especially given that its cloud-edge collaborative deployment offers cloud workload offloading, offline robustness, and privacy enhancement. However, existing collaborative inference frameworks with speculative decoding are constrained…
The parameter size of modern large language models (LLMs) can be scaled up to the trillion-level via the sparsely-activated Mixture-of-Experts (MoE) technique to avoid excessive increase of the computational costs. To further improve training efficiency, pipelining computation and communication has…
In-context learning (ICL) and Retrieval-Augmented Generation (RAG) have gained attention for their ability to enhance LLMs' reasoning by incorporating external knowledge but suffer from limited contextual window size, leading to insufficient information injection. To this end, we propose a novel fra…
We consider the robust routing problem with uncertain travel times under the min-max regret criterion, which represents an extended and robust version of the classic traveling salesman problem (TSP) and vehicle routing problem (VRP). The general budget uncertainty set is employed to capture the unce…
A well known problem of regularization (diagonal loading) of the interference rejection combining (IRC) and IRC / maximum ratio combining (MRC) switching is addressed. Different empirical loading factor selection rules adjusted to specific scenarios have been introduced in the literature. It is expe…