arXiv Computer Vision November 2, 2026 By Zhiqi Zhang, Xinhao Zhong, Yi Sun, Shuoyang Sun, Jiahui Wang, Bin Chen, Shu-Tao Xia, Xuan Wang

Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models

Read the original on arXiv Computer Vision →

The paper introduces Differential Vector Erasure (DVE), a training‑free method for removing unwanted concepts from flow matching image generation models. DVE exploits the directional structure of the velocity field that encodes semantic concepts, constructing a differential vector field to isolate and suppress target concepts during inference. Experiments on the FLUX model show that DVE outperforms existing baselines in tasks such as NSFW suppression, style removal, and object erasure while maintaining image quality and diversity.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

Jun 2

Geometric Erasure by Contrastive Velocity Matching in Rectified Flows

arXiv:2606. 00140v1 Announce Type: cross Abstract: 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.

By Jonas Henry Grebe, Tobias Braun, Anna Rohrbach, Marcus Rohrbach

llms diffusion multimodal

arXiv AI

Jul 8

TILDE: TILt-based Distributional Erasure for Concept Unlearning

arXiv:2607. 06432v1 Announce Type: cross Abstract: Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment: with rising privacy concerns, copyright disputes, trademark constraints, and safety regulations, deployed systems must be able to suppress unwanted concepts after training.

By Naveen George, Naoki Murata, Yuhta Takida, Konda Reddy Mopuri, Yuki Mitsufuji

diffusion safety

arXiv AI

Aug 21

GEM: Geometric Erasure by Contrastive Velocity Matching in Rectified Flows

arXiv:2606. 00140v3 Announce Type: replace-cross Abstract: 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.

By Jonas Henry Grebe, Tobias Braun, Anna Rohrbach, Marcus Rohrbach

llms diffusion multimodal

arXiv Machine Learning

Jul 28

To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion

arXiv:2607. 23492v1 Announce Type: cross Abstract: Concept erasure techniques (CETs) edit text-to-image diffusion models to erase undesired targets such as NSFW content or copyrighted styles, while preserving model utility on benign concepts.

By Shaswati Saha, Rajasekhar Anguluri, Manas Gaur

llms diffusion multimodal

arXiv Computer Vision

Oct 2

RASteer: Retain-Aware Activation Steering for Concept Erasure in Diffusion Models

RASteer is a training‑free method for concept erasure in text‑to‑image diffusion models that retains other concepts. It constructs a retain subspace from concepts to preserve, then removes components aligned with this subspace from the erasure direction using Retain‑Orthogonal Steering (ROS). Overlap‑Adaptive Calibration (OAC) further adjusts the removal of shared components at each layer and denoising step, balancing target erasure with concept preservation. Experiments show RASteer matches or outperforms existing activation steering and weight editing baselines on unsafe‑content, instance, and artistic‑style erasure tasks across multiple backbones and benchmarks.

By Yongliang Wu, Haori Lu, Yulun Wu, Jinqi Luo, Xingyu Zhu, Yaoyao Liu

diffusion benchmarks

arXiv AI

Jun 16

SACE: Concept Erasure at the Semantic Singularity in Visual Autoregressive Models

arXiv:2606. 15819v1 Announce Type: cross Abstract: The rapid progress of visual autoregressive (VAR) models has unlocked a transformative frontier for high-fidelity text-to-image synthesis, while heightening concerns over the safety alignment of generated content.

By Siya Yang, Nanxiang Jiang, Zhaoxin Fan, Yunfeng Diao

diffusion safety

One email a morning, machine-written

Related stories

Geometric Erasure by Contrastive Velocity Matching in Rectified Flows

TILDE: TILt-based Distributional Erasure for Concept Unlearning

GEM: Geometric Erasure by Contrastive Velocity Matching in Rectified Flows

To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion

RASteer: Retain-Aware Activation Steering for Concept Erasure in Diffusion Models

SACE: Concept Erasure at the Semantic Singularity in Visual Autoregressive Models