Inspired by non-equilibrium thermodynamics, diffusion models have achieved state-of-the-art performance in generative modeling. However, their iterative sampling nature results in high inference latency. While recent distillation techniques accelerate sampling, they discard intermediate trajectory steps. This sparse supervision leads to a loss of structural information and introduces significant discretization errors. To mitigate this, we propose B-DENSE, a novel framework that leverages multi-branch trajectory alignment. We modify the student architecture to output $K$-fold expanded channels, where each subset corresponds to a specific branch representing a discrete intermediate step in the teacher's trajectory. By training these branches to simultaneously map to the entire sequence of the teacher's target timesteps, we enforce dense intermediate trajectory alignment. Consequently, the student model learns to navigate the solution space from the earliest stages of training, demonstrating superior image generation quality compared to baseline distillation frameworks.

翻译：受非平衡热力学启发，扩散模型在生成建模领域取得了最先进的性能。然而，其迭代采样的特性导致较高的推理延迟。尽管近期的蒸馏技术能够加速采样过程，但它们舍弃了中间轨迹步骤。这种稀疏监督会导致结构信息丢失并引入显著的离散化误差。为缓解此问题，我们提出了B-DENSE——一种利用多分支轨迹对齐的新型框架。我们改进学生架构以输出$K$倍扩展的通道，其中每个子集对应代表教师轨迹中特定离散中间步骤的分支。通过训练这些分支同时映射到教师目标时间步的完整序列，我们实现了密集的中间轨迹对齐。因此，学生模型从训练的最初阶段就学会在解空间中导航，与基线蒸馏框架相比展现出更优越的图像生成质量。