Doubao: VideoWorld, a video generation model that can perceive the world based on vision alone, is now open source

PANews, February 10 news, the video generation experimental model "VideoWorld" was proposed by the Douban Large Model Team, Beijing Jiaotong University, and the University of Science and Technology of China. Unlike mainstream multimodal models such as Sora, DALL-E, and Midjourney, VideoWorld is the first in the industry to achieve cognition of the world without relying on language models. Currently, the project code and model have been open-sourced.