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.

Researchers baked 3x inference speedups directly into LLM weights — without speculative decoding

Researchers from the University of Maryland, Lawrence Livermore, Columbia and TogetherAI have developed a training technique that triples LLM inference speed without auxiliary models or infrastructure ...
IEEE

A Mixed Integer Linear Programming Model for Robotic Flow Shop Scheduling with Multi-type Parts Production

Abstract: Automated manufacturing systems integrate sequential processing machines with material handling robots to transport jobs between stages, enhancing productivity and efficiency. Such systems ...
IEEE

Multi-Sensor Model for Earth Observation Robust to Missing Data via Sensor Dropout and Mutual Distillation

Abstract: Multi-sensor data has become a foundation of Earth Observation (EO) research, offering models with enhanced accuracy via optimal fusion strategies. However, the unavailability of sensor data ...