Training-Free Reward-Guided Image Editing via Trajectory Optimal Control

ArXi:2509.25845v3 Announce Type: replace-cross Recent advancements in diffusion and flow-matching models have nstrated remarkable capabilities in high-fidelity image synthesis. A prominent line of research involves reward-guided guidance, which steers the generation process during inference to align with specific objectives. However, leveraging this reward-guided approach to the task of image editing, which requires preserving the semantic content of the source image while enhancing a target reward, is largely unexplored. In this work, we