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

Car-Following Speed Prediction and Anomaly Detection for Mixed Traffic Flow of Autonomous Vehicle Based on Attention LSTM–Transformer

Abstract: In an autonomous vehicle-mixed traffic flow (AV-MTF) environment, accurately predicting vehicle speeds is essential for vehicle and traffic operation and management. However, existing ...
IEEE

Short-Term Rainfall Prediction from Satellite Images Using Convolutional-LSTM Models

Abstract: Short-term rainfall prediction is a meteorological forecast aimed at accurately predicting rainfall intensity within the next few hours for a specific region. Previous methods were ...