SenseTime showcases the newly upgraded SenseNova 5.5 large model system and autonomous driving solutions

SenseTime showcased the newly upgraded SenseNova 5.5 big model system and autonomous driving solution UniAD and DriveAGI multimodal big model at the 2024 World Artificial Intelligence Conference. SenseNova 5.5 is the first officially released streaming native multimodal interaction model in China, which integrates cross-modal information based on multiple forms such as sound, text, images and videos. UniAD can efficiently and accurately complete a series of difficult operations on various complex urban roads and rural roads without center lines. DriveAGI multimodal big model promotes the transition of autonomous driving from data-driven to cognitive-driven.