RADS：用可达性约束强化学习让文本到图像扩散模型摆脱记忆化

View PDF HTML (experimental)

Abstract:Text-to-image diffusion models are susceptible to memorization, revealing a fundamental failure to generalize beyond the training set. Current mitigation approaches often sacrifice image quality or prompt alignment to reduce memorization. To address this, we propose Reachability-Aware Diffusion Steering (RADS), an offline-trained, sampling-time control framework that mitigates memorization while maintaining generation fidelity. RADS models the diffusion denoising process as a dynamical system and learns a policy-conditioned reachability value function that estimates future memorization risk along the denoising trajectory. This motivates a constrained reinforcement learning (RL) formulation, where a policy learns to steer the trajectory away from memorization via perturbations in the caption embedding space. Empirical evaluations show that RADS achieves a stronger empirical Pareto frontier between generation diversity (SSCD), quality (FID), and alignment (CLIP) compared to state-of-the-art inference-time baselines. Crucially, RADS applies the learned controller during sampling time, separating memorization mitigation from the pretrained model. Our website is available at: this https URL.

Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
Cite as:	arXiv:2603.00140 [cs.CV]
	(or arXiv:2603.00140v2 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2603.00140 arXiv-issued DOI via DataCite

Submission history

From: Sathwik Karnik [view email]
[v1] Tue, 24 Feb 2026 09:07:08 UTC (16,350 KB)
[v2] Wed, 11 Nov 2026 23:25:27 UTC (43,202 KB)