Critic-Guided Reinforcement Unlearning in Text-to-Image Diffusion

Machine unlearning in text-to-image diffusion models aims to remove targeted concepts while preserving overall utility. Prior diffusion unlearning methods typically rely on supervised weight edits or global penalties; reinforcement-learning (RL) approaches, while flexible, often optimize sparse end-of-trajectory rewards, yielding high-variance updates and weak credit assignment. We present a general RL framework for diffusion unlearning that treats denoising as a sequential decision process and introduces a timestep-aware critic with noisy-step rewards. Concretely, we train a CLIP-based reward predictor on noisy latents and use its per-step signal to compute advantage estimates for policy-gradient updates of the reverse diffusion kernel. Our algorithm is simple to implement, supports off-policy reuse, and plugs into standard text-to-image backbones. Across multiple concepts, the method achieves better or comparable forgetting to strong baselines while maintaining image quality and benign prompt fidelity; ablations show that (i) per-step critics and (ii) noisy-conditioned rewards are key to stability and effectiveness. We release code and evaluation scripts to facilitate reproducibility and future research on RL-based diffusion unlearning.

License Plate Images Generation with Diffusion Models

Despite the evident practical importance of license plate recognition (LPR), corresponding research is limited by the volume of publicly available datasets due to privacy regulations such as the General Data Protection Regulation (GDPR). To address this challenge, synthetic data generation has emerged as a promising approach. In this paper, we propose to synthesize realistic license plates (LPs) using diffusion models, inspired by recent advances in image and video generation. In our experiments a diffusion model was successfully trained on a Ukrainian LP dataset, and 1000 synthetic images were generated for detailed analysis. Through manual classification and annotation of the generated images, we performed a thorough study of the model output, such as success rate, character distributions, and type of failures. Our contributions include experimental validation of the efficacy of diffusion models for LP synthesis, along with insights into the characteristics of the generated data. Furthermore, we have prepared a synthetic dataset consisting of 10,000 LP images, publicly available at https://zenodo.org/doi/10.5281/zenodo.13342102. Conducted experiments empirically confirm the usefulness of synthetic data for the LPR task. Despite the initial performance gap between the model trained with real and synthetic data, the expansion of the training data set with pseudolabeled synthetic data leads to an improvement in LPR accuracy by 3% compared to baseline.