Generative models based on flow matching have demonstrated remarkable success in various domains, yet they suffer from a fundamental limitation: the lack of interpretability in their intermediate generation steps. In fact these models learn to transform noise into data through a series of vector field updates, however the meaning of each step remains opaque. We address this problem by proposing a general framework constraining each flow step to be sampled from a known physical distribution. Flow trajectories are mapped to (and constrained to traverse) the equilibrium states of the simulated physical process. We implement this approach through the 2D Ising model in such a way that flow steps become thermal equilibrium points along a parametric cooling schedule. Our proposed architecture includes an encoder that maps discrete Ising configurations into a continuous latent space, a flow-matching network that performs temperature-driven diffusion, and a projector that returns to discrete Ising states while preserving physical constraints. We validate this framework across multiple lattice sizes, showing that it preserves physical fidelity while outperforming Monte Carlo generation in speed as the lattice size increases. In contrast with standard flow matching, each vector field represents a meaningful stepwise transition in the 2D Ising model's latent space. This demonstrates that embedding physical semantics into generative flows transforms opaque neural trajectories into interpretable physical processes.
翻译:基于流匹配的生成模型在多个领域取得了显著成功,但其存在一个根本性局限:中间生成步骤缺乏可解释性。实际上,这些模型通过学习一系列向量场更新将噪声转化为数据,然而每个步骤的含义仍然是不透明的。我们通过提出一个通用框架来解决此问题,该框架约束每个流步骤必须从已知的物理分布中采样。流轨迹被映射(并约束其遍历)至模拟物理过程的平衡态。我们通过二维伊辛模型实现该方法,使得流步骤成为沿参数化冷却进程的热平衡点。我们提出的架构包括:将离散伊辛构型映射到连续潜在空间的编码器、执行温度驱动扩散的流匹配网络,以及返回离散伊辛状态同时保持物理约束的投影器。我们在多种晶格尺寸上验证该框架,结果表明其在保持物理保真度的同时,随着晶格尺寸增大,在生成速度上超越了蒙特卡洛方法。与标准流匹配相比,每个向量场代表了二维伊辛模型潜在空间中具有明确意义的逐步转变。这证明将物理语义嵌入生成流中,可将不透明的神经轨迹转化为可解释的物理过程。