图灵奖得主Yann LeCun在2024年世界经济论坛会谈中指出，当前流行的生成模型并不适合处理视频数据。他认为，处理视频的AI模型应该能够在抽象表征空间中进行预测，而非在像素空间中。这一观点为AI技术的未来发展提供了新的思路。
Title: Generating Models Inadequate for Video Processing
Keywords: Generating Models, Video Processing, Abstract Space
News content: Turing Award winner Yann LeCun stated during a discussion at the 2024 World Economic Forum that the prevalent generative models are not suitable for video data processing. He believes that AI models for video should predict in an abstract representation space rather than in pixel space, offering a new perspective for the development of AI technology.
【来源】https://mp.weixin.qq.com/s/sAWFkcTFfZVJ_oLKditqVA
Views: 1