February 10, 2011 - VideoWorld, an experimental model for video generation jointly developed by Beanbag Big Model Team, Beijing Jiaotong University and University of Science and Technology of China, is open-sourced today. Unlike Sora, DALL-E, Midjourney and other mainstream multimodal model, VideoWorld in the industry for the first time without relying on language models, you can know the world. According to the introduction, most of the existing models rely on language or labeled data to learn knowledge, and seldom involve the learning of pure visual signals. However, language does not capture all knowledge in the real world. For example, origami ...