Image de couverture de livre

Erasing Concepts, Steering Generations: A Comprehensive Survey of Concept Suppression

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xie, Yiwei, Liu, Ping, Zhang, Zheng
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

PROBE: Diagnosing Residual Concept Capacity in Erased Text-to-Video Diffusion Models
par: Xie, Yiwei, et autres
Publié: (2026)

Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models
par: Xie, Yiwei, et autres
Publié: (2026)

Erased or Dormant? Rethinking Concept Erasure Through Reversibility
par: Liu, Ping, et autres
Publié: (2025)

Bi-Erasing: A Bidirectional Framework for Concept Removal in Diffusion Models
par: Chen, Hao, et autres
Publié: (2025)

Erasing More Than Intended? How Concept Erasure Degrades the Generation of Non-Target Concepts
par: Amara, Ibtihel, et autres
Publié: (2025)

Erased, But Not Forgotten: Erased Rectified Flow Transformers Still Remain Unsafe Under Concept Attack
par: Jiang, Nanxiang, et autres
Publié: (2025)

Pruning for Robust Concept Erasing in Diffusion Models
par: Yang, Tianyun, et autres
Publié: (2024)

Do Concept Replacement Techniques Really Erase Unacceptable Concepts?
par: Das, Anudeep, et autres
Publié: (2025)

EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers
par: Gao, Daiheng, et autres
Publié: (2024)

Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers
par: Jiang, Nanxiang, et autres
Publié: (2026)

EAR: Erasing Concepts from Unified Autoregressive Models
par: Fan, Haipeng, et autres
Publié: (2025)

Beyond Fixed Anchors: Precisely Erasing Concepts with Sibling Exclusive Counterparts
par: Zhang, Tong, et autres
Publié: (2025)

ESC: Erasing Space Concept for Knowledge Deletion
par: Lee, Tae-Young, et autres
Publié: (2025)

When Are Concepts Erased From Diffusion Models?
par: Lu, Kevin, et autres
Publié: (2025)

Concept Corrector: Erase concepts on the fly for text-to-image diffusion models
par: Meng, Zheling, et autres
Publié: (2025)

T2VUnlearning: A Concept Erasing Method for Text-to-Video Diffusion Models
par: Ye, Xiaoyu, et autres
Publié: (2025)

Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision Localization
par: Zhang, Lingyun, et autres
Publié: (2024)

Side Effects of Erasing Concepts from Diffusion Models
par: Saha, Shaswati, et autres
Publié: (2025)

Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
par: Bui, Anh, et autres
Publié: (2024)

Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models
par: Seo, Hoigi, et autres
Publié: (2026)

FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models
par: Sun, Yi, et autres
Publié: (2026)

Prompt Sliders for Fine-Grained Control, Editing and Erasing of Concepts in Diffusion Models
par: Sridhar, Deepak, et autres
Publié: (2024)

SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders
par: Cassano, Enrico, et autres
Publié: (2025)

ActErase: A Training-Free Paradigm for Precise Concept Erasure via Activation Redirection
par: Sun, Yi, et autres
Publié: (2026)

Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models
par: Gao, Daiheng, et autres
Publié: (2025)

A Comprehensive Survey on Visual Concept Mining in Text-to-image Diffusion Models
par: Li, Ziqiang, et autres
Publié: (2025)

STEREO: A Two-Stage Framework for Adversarially Robust Concept Erasing from Text-to-Image Diffusion Models
par: Srivatsan, Koushik, et autres
Publié: (2024)

Erasing Concepts from Text-to-Image Diffusion Models with Few-shot Unlearning
par: Fuchi, Masane, et autres
Publié: (2024)

EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment
par: Kusumba, Abhiram, et autres
Publié: (2025)

Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers
par: Huang, Chi-Pin, et autres
Publié: (2023)

Erasing with Precision: Evaluating Specific Concept Erasure from Text-to-Image Generative Models
par: Fuchi, Masane, et autres
Publié: (2025)

You Only Erase Once: Erasing Anything without Bringing Unexpected Content
par: Zhu, Yixing, et autres
Publié: (2026)

A Comprehensive Survey on Concept Erasure in Text-to-Image Diffusion Models
par: Kim, Changhoon, et autres
Publié: (2025)

SAGE: Exploring the Boundaries of Unsafe Concept Domain with Semantic-Augment Erasing
par: Zhu, Hongguang, et autres
Publié: (2025)

RealEra: Semantic-level Concept Erasure via Neighbor-Concept Mining
par: Liu, Yufan, et autres
Publié: (2024)

EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimization
par: Fan, Zhaoxin, et autres
Publié: (2026)

Growth Inhibitors for Suppressing Inappropriate Image Concepts in Diffusion Models
par: Chen, Die, et autres
Publié: (2024)

Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models
par: Tian, Zhihua, et autres
Publié: (2025)

CoBELa: Steering Transparent Generation via Concept Bottlenecks on Energy Landscapes
par: Kim, Sangwon, et autres
Publié: (2025)

Causal Physics Steering in Video World Models via Concept Activation Vectors
par: Alam, Nahid
Publié: (2026)