复杂度平衡扩散分裂

摘要

标准的连续时间生成模型依赖于单一架构，必须应对从各向同性噪声到复杂数据分布等截然不同的信号区域。虽然扩大模型容量可以提升性能，但在整个生成时间线上均匀部署一个大型网络本质上效率低下。在本工作中，我们提出复杂度平衡分割方法（CBS），这是一种时间容量分配的原则性框架，通过将生成工作负载分布到多个专业化子网络来实现。基于函数逼近理论和De Boor等分布原理，CBS将扩散时间线划分为近似负担相等的片段，将更多表示能力分配给生成动力学更难建模的区域。为了估计这种局部复杂度，我们引入了两种互补且可计算的监测函数：一种基于流形狄利克雷能量的空间测度，另一种基于采样轨迹加速度的几何测度。通过使用轻量级辅助模型估计这些复杂度轮廓，我们的方法消除了对启发式时间分割或计算昂贵的搜索过程的需求。在多种架构（SiT、JiT和UNet）和数据集上的广泛评估表明，CBS能够在不增加每步推理成本的情况下持续提升合成质量。特别地，在采用CFG的SiT-XL上，CBS相对于朴素时间分割将FID改善了约35%。项目页面见https://noamissachar.github.io/CBS/。

English

Standard continuous-time generative models rely on monolithic architectures that must navigate vastly different signal regimes, from isotropic noise to intricate data distributions. While scaling model capacity improves performance, deploying a massive network uniformly across the entire generative timeline is inherently inefficient. In this work, we propose Complexity-Balanced Splitting (CBS), a principled framework for temporal capacity allocation that distributes the generative workload across multiple specialized sub-networks. Grounded in function approximation theory and de Boor's equidistribution principle, CBS partitions the diffusion timeline into segments of equal approximation burden, allocating more representational capacity to regions where the generative dynamics are more difficult to model. To estimate this local complexity, we introduce two complementary and tractable monitor functions: a spatial measure based on the flow's Dirichlet energy, and a geometric measure based on the acceleration of the sampling trajectories. Using a lightweight auxiliary model to estimate these complexity profiles, our approach eliminates the need for heuristic temporal splits or computationally expensive search procedures. Extensive evaluation across multiple architectures (SiT, JiT, and UNet) and datasets demonstrates that CBS consistently improves synthesis quality without increasing per-step inference cost. In particular, CBS improves FID by ~35% on SiT-XL with CFG relative to naive temporal partitioning. Project page is available at https://noamissachar.github.io/CBS/.