#1 LeCun又出一篇关于世界模型的论文
发表于 ： 2025年 3月 12日 21:43
https://zhuanlan.zhihu.com/p/2751205137 ... 1438450885
https://arxiv.org/pdf/2502.11831
https://arxiv.org/html/2502.11831
Abstract
We investigate the emergence of intuitive physics understanding in general-purpose deep neural network models trained to predict masked regions in natural videos. Leveraging the violation-of-expectation framework, we find that video prediction models trained to predict outcomes in a learned representation space demonstrate an understanding of various intuitive physics properties, such as object permanence and shape consistency. In contrast, video prediction in pixel space and multimodal large language models, which reason through text, achieve performance closer to chance. Our comparisons of these architectures reveal that jointly learning an abstract representation space while predicting missing parts of sensory input, akin to predictive coding, is sufficient to acquire an understanding of intuitive physics, and that even models trained on one week of unique video achieve above chance performance. This challenges the idea that core knowledge — a set of innate systems to help understand the world — needs to be hardwired to develop an understanding of intuitive physics.
https://arxiv.org/pdf/2502.11831
https://arxiv.org/html/2502.11831
Abstract
We investigate the emergence of intuitive physics understanding in general-purpose deep neural network models trained to predict masked regions in natural videos. Leveraging the violation-of-expectation framework, we find that video prediction models trained to predict outcomes in a learned representation space demonstrate an understanding of various intuitive physics properties, such as object permanence and shape consistency. In contrast, video prediction in pixel space and multimodal large language models, which reason through text, achieve performance closer to chance. Our comparisons of these architectures reveal that jointly learning an abstract representation space while predicting missing parts of sensory input, akin to predictive coding, is sufficient to acquire an understanding of intuitive physics, and that even models trained on one week of unique video achieve above chance performance. This challenges the idea that core knowledge — a set of innate systems to help understand the world — needs to be hardwired to develop an understanding of intuitive physics.