FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models 事件

FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models arXiv:2605.19739v2 Announce Type: replace Abstract: Recent advances in flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks due to the generation of harmful or undesirable content. Existing concept erasure methods are either inference-time interventions with limited effectiveness or rely on supervised fine-tuning (SFT), which requires prec