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

Celestial Trajectory Prediction

Abstract: Detecting the trajectories of celestial bodies is fundamental to space exploration, spacecraft safety, and astrophysical studies. Although completely physics-based models provide a reliable ...
IEEE

A time sequence multimodal deep learning method combining acceleration and frequency domain signal for bearing fault diagnosis

Abstract: The performance of traditional bearing fault diagnosis methods is substantially improved by applying deep learning methods. However, enhancement in the accuracy of prevailing unimodal ...