InfoWorld

Multi-token prediction technique triples LLM inference speed without auxiliary draft models

With reported 3x speed gains and limited degradation in output quality, the method targets one of the biggest pain points in production AI systems: latency at scale.
IEEE

It’s Morphing Time: Unleashing the Potential of Multiple LLMs via Multi-Objective Optimization

Abstract: In this paper, we introduce a novel approach for addressing the multi-objective optimization problem in large language model merging via black-box multi-objective optimization algorithms.
IEEE

Privacy-Preserving Computation Offloading and 3-D Trajectory Optimization in Multi-UAV-Assisted MEC System

Abstract: Due to the flexibility in the deployment of unmanned aerial vehicles (UAVs), UAV-assisted mobile edge computing (MEC) systems have garnered significant attention in recent years. Users can ...