This paper does not describe a working system. Instead, it presents a single idea about representation which allows advances made by several different groups to be combined into an imaginary system called GLOM. The advances include transformers, neural fields, contrastive representation learning, distillation and capsules. GLOM answers the question: How can a neural network with a fixed architecture parse an image into a part-whole hierarchy which has a different structure for each image? The idea is simply to use islands of identical vectors to represent the nodes in the parse tree. If GLOM can be made to work, it should significantly improve the interpretability of the representations produced by transformer-like systems when applied to vision or language
I love the abstract level on which luminary scientists who still choose to contribute write papers. This is perhaps the best example I've seen. Each section is a distillation of knowledge spanning multiple fields of study and decades of results. This made my day. When humanity is without GH we will truly be weaker.