BRo-JEPA：让世界模型学会模块化代数规则 BRo-JEPA: Learning Modular Transformations in Latent Space

精读摘要

神经网络是从视觉输入中学到了代数规则，还是只是在拟合观察到的模式？研究用 MNIST/EMNIST 字母作为状态、模运算作为动作，在 JEPA 式世界模型中检验这个问题。标准监督方法与 JEPA 基线在见过的运算上精度很高，却无法可靠外推到未见的运算。BRo-JEPA 引入块旋转预测器，把算术运算表示为旋转，形成循环结构，从而学会可外推的模块化变换。 Can neural networks learn algebraic rules from visual inputs, or do they merely fit observed patterns? Using MNIST or EMNIST letters as states and modular arithmetic as actions in a JEPA-style world model, standard baselines achieve high accuracy on seen operations but fail to extrapolate to unseen ones. BRo-JEPA introduces a block-rotation predictor that represents arithmetic operations as rotations, yielding cyclic structure and extrapolatable modular transformations.