Short-Window Dynamics for Configuration Screening in Controlled Diffusion

Inference-time control often requires searching over intervention operators, strengths, source weights, and temporal schedules. Running a complete denoising trajectory for every candidate quickly becomes expensive. We present \method, a training-free screening method that probes only a short reverse-denoising window in each active control stage. From these local trajectories, \method measures control response, propagation gain, directional conflict with the native denoising update, and relative intervention magnitude. For tasks with explicit source constraints, these generic diagnostics can be paired with a lightweight consistency check. The measurements are summarized at the stage level, aggregated across a multi-stage schedule, and used to decide which configurations continue to full sampling. On a dual-source AFHQ-Dog testbed, we collect 109,080 seven-step traces from 5,454 configurations. Among 3,780 effective two-stage configurations, the screen rejects 18.67% of sample–configuration pairs overall and 60.30% for Laplacian high-frequency control. On 90 fully sampled cases, accepted and rejected groups show clear separation in source-consistency metrics; the screening margin correlates with reference SSIM ($\rho =0.645$) and reference low-frequency distance ($\rho =-0.724$). The results show that short local trajectories contain useful information for reducing controlled-diffusion configuration search.