PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment

ArXi:2510.00430v2 Announce Type: replace Despite recent progress, reinforcement learning (RL)-based fine-tuning of diffusion models often struggles with generalization, composability, and robustness against reward hacking. Recent studies have explored prompt refinement as a modular alternative, but most adopt a feed-forward approach that applies a single refined prompt throughout the entire sampling trajectory, thereby failing to fully leverage the sequential nature of reinforcement learning. To address this, we.