Inference-Time Attribute Distribution Alignment for Unconditional Diffusion

ArXi:2605.07456v1 Announce Type: new Inference-time controllable generation is essential for real-world applications of unconditional diffusion models. However, most existing techniques focus on individual samples, struggling in applications that require the sample population to follow specific attribute distributions (e.g., graphic balance or semantic proportions). We formalize this setting as the inference-time attribute distributional alignment problem for pretrained unconditional diffusion models.