在2024世界经济论坛的一次会谈中，图灵奖得主、Meta首席AI科学家Yann LeCun针对“如何让AI理解视频数据”的问题发表了自己的看法。他认为，目前广泛应用的生成模型并不适合处理视频数据。Yann LeCun指出，新的AI模型应当学会在抽象的表征空间中进行预测，而非在像素空间中。这一观点对于当前AI技术在视频领域的应用具有重要意义。
Title: Meta Chief AI Scientist: Generative Models Unsuitable for Video Processing
Keywords: AI, Video Processing, Abstract Prediction
News content: At the 2024 World Economic Forum, Yann LeCun, winner of the Turing Award and Chief AI Scientist at Meta, expressed his views on “How to Make AI Understand Video Data”. He believes that the widely used generative models are not suitable for processing video data. Yann LeCun pointed out that new AI models should learn to predict in the abstract representation space rather than in the pixel space. This view is of great significance for the application of current AI technology in the field of video.
【来源】https://mp.weixin.qq.com/s/sAWFkcTFfZVJ_oLKditqVA
Views: 1