这篇论文把专家组合从全局加权改成了因子级路由，在ARC-AGI上效果更好，适合研究离散扩散或组合生成的人看。
离散扩散模型通过组合多个预训练专家实现复杂推理生成，但现有方法基于全样本加权，忽略了专家在空间或功能上的特化。本文提出FactorDiff，将生成样本分解为更小的因子，并在采样过程中动态路由每个因子到最相关专家。FactorDiff在ARC-AGI基准上验证了空间/像素级组合，其简单因子级路由在需要逻辑一致性和空间解耦的任务上持续优于复杂的全局标量加权方案。
From Global to Factor-Wise Expert Composition in Discrete Diffusion Models
Discrete diffusion models offer a powerful framework for solving complex reasoning tasks, particularly through compositional generation, which combines multiple pre-trained experts to generalize beyond their individual training data. Recent theoretical corrections introduce time-dependent mixing weights to better align composed diffusion dynamics with the intended target. However, these methods are fundamentally limited by working on a per-sample basis, treating each generated state monolithically and ignoring the potential spatial or functional specializations of different experts. In this work, we address this limitation by proposing FactorDiff - a factor-wise composition framework for diffusion models. We posit that samples can be further decomposed into smaller factors, and propose a sampling process that dynamically routes each factor to the most relevant expert. We instantiate this framework with spatial/pixel-level compositions and validate it on the ARC-AGI benchmark, demonstrating that simple factor-specific routing consistently outperforms complex global scalar weighting schemes on tasks that require logical consistency and spatial disentanglement.