轨迹链：通过图论规划解锁扩散模型内在的生成最优性

摘要

扩散模型在反射性的系统1模式下运行，受限于固定且内容无关的采样规划。这种刚性源于状态维度的诅咒——高维噪声流形中可能状态的组合爆炸使得显式轨迹规划难以实现，并导致系统性的计算资源错配。为此，我们提出轨迹链（CoTj）这一免训练框架，实现系统2的审慎规划能力。其核心是扩散DNA：一种量化各阶段去噪难度的低维特征标识，可作为高维状态空间的代理表征，使我们能够将有向无环图上的图规划重构为采样过程。通过"预测-规划-执行"范式，CoTj将计算资源动态分配给最具挑战性的生成阶段。在多类生成模型上的实验表明，CoTj能发现上下文感知的轨迹，在提升输出质量与稳定性的同时减少冗余计算。本研究为基于资源感知与规划思维的扩散建模奠定了新基础。代码已开源：https://github.com/UnicomAI/CoTj。

English

Diffusion models operate in a reflexive System 1 mode, constrained by a fixed, content-agnostic sampling schedule. This rigidity arises from the curse of state dimensionality, where the combinatorial explosion of possible states in the high-dimensional noise manifold renders explicit trajectory planning intractable and leads to systematic computational misallocation. To address this, we introduce Chain-of-Trajectories (CoTj), a train-free framework enabling System 2 deliberative planning. Central to CoTj is Diffusion DNA, a low-dimensional signature that quantifies per-stage denoising difficulty and serves as a proxy for the high-dimensional state space, allowing us to reformulate sampling as graph planning on a directed acyclic graph. Through a Predict-Plan-Execute paradigm, CoTj dynamically allocates computational effort to the most challenging generative phases. Experiments across multiple generative models demonstrate that CoTj discovers context-aware trajectories, improving output quality and stability while reducing redundant computation. This work establishes a new foundation for resource-aware, planning-based diffusion modeling. The code is available at https://github.com/UnicomAI/CoTj.

轨迹链：通过图论规划解锁扩散模型内在的生成最优性

Chain-of-Trajectories: Unlocking the Intrinsic Generative Optimality of Diffusion Models via Graph-Theoretic Planning

摘要

Support