提出GEM框架，实现对修正流模型中特定概念的精准擦除。
GEM: Geometric Erasure by Contrastive Velocity Matching in Rectified Flows
- 将轨迹信号转化为教师引导的几何指引，统一两类擦除方法。
- 通过吸引与排斥信号联合优化，有效抑制目标概念生成。
- 适用于修正流架构，为多模态生成内容安全提供新方案。
尽管多模态生成模型的快速应用带来了巨大潜力，但也增加了有害内容合成、深度伪造和版权侵权的风险。为应对这些挑战，概念擦除作为一种有前景的防护手段应运而生。然而，随着该领域逐步从基于U-Net的扩散模型转向修正流变换器，擦除研究却未能同步跟进。本文提出GEM，一种针对修正流模型的简单但高效的擦除框架。作为贡献之一，我们建立了一条连接基于轨迹的生成流网络无学习与经典教师引导擦除的理论桥梁：将轨迹信号转化为教师引导的流匹配设置，融合两类范式的优点。具体而言，教师提供互补的吸引与排斥信号，我们将其整合为单一几何指引目标，在抑制特定概念的同时保持良性生成能力。
原文摘要 · Abstract (English)
While the rapid adoption of multimodal generative models offers immense potential, it has also increased the risks of harmful content synthesis, deepfakes, and copyright infringements. To address these challenges, concept erasure has emerged as a prospective safeguard. However, as the field gradually transitions from U-Net-based diffusion models to Rectified Flow Transformers, erasure research has struggled to keep pace. In this work, we introduce GEM, a simple but highly effective erasure framework for Rectified Flow models. As part of our contribution, we establish a principled bridge between trajectory-based unlearning grounded in Generative Flow Networks and classic teacher-guided erasure: we translate trajectory-based signals into a teacher-guided flow-matching setup that unifies the strengths of both paradigms. Concretely, a teacher provides complementary attraction and repulsion signals that we combine into a single geometric guidance objective, yielding targeted suppression of unwanted concepts while preserving benign generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。