Copertina

Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation Misdirection

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lee, Uichan, Kim, Jeonghyeon, Hwang, Sangheum
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations
di: Kim, Jeonghyeon, et al.
Pubblicazione: (2025)

Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation
di: Kim, Jihyo, et al.
Pubblicazione: (2024)

A Comprehensive Survey on Concept Erasure in Text-to-Image Diffusion Models
di: Kim, Changhoon, et al.
Pubblicazione: (2025)

Parallel Rescaling: Rebalancing Consistency Guidance for Personalized Diffusion Models
di: Chae, JungWoo, et al.
Pubblicazione: (2025)

Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models
di: Seo, Hoigi, et al.
Pubblicazione: (2026)

Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank Adaptation
di: Lee, Byung Hyun, et al.
Pubblicazione: (2025)

TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models
di: Chen, Ruidong, et al.
Pubblicazione: (2025)

CRCE: Coreference-Retention Concept Erasure in Text-to-Image Diffusion Models
di: Xue, Yuyang, et al.
Pubblicazione: (2025)

CE-SDWV: Effective and Efficient Concept Erasure for Text-to-Image Diffusion Models via a Semantic-Driven Word Vocabulary
di: Tu, Jiahang, et al.
Pubblicazione: (2025)

VideoEraser: Concept Erasure in Text-to-Video Diffusion Models
di: Xu, Naen, et al.
Pubblicazione: (2025)

Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending
di: Ko, Junseok, et al.
Pubblicazione: (2026)

Mass Concept Erasure in Diffusion Models with Concept Hierarchy
di: Tu, Jiahang, et al.
Pubblicazione: (2026)

Dynamic Eraser for Guided Concept Erasure in Diffusion Models
di: Gong, Qinghui
Pubblicazione: (2026)

Zero-Residual Concept Erasure via Progressive Alignment in Text-to-Image Model
di: Chen, Hongxu, et al.
Pubblicazione: (2025)

Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models
di: Xiong, Lexiang, et al.
Pubblicazione: (2025)

MACE: Mass Concept Erasure in Diffusion Models
di: Lu, Shilin, et al.
Pubblicazione: (2024)

Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them
di: Bui, Anh, et al.
Pubblicazione: (2025)

Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models
di: Kim, Sanghyun, et al.
Pubblicazione: (2024)

Focusing Where Vision Matters: Selective Training for Large Vision Language Models via Visual Information Gain
di: Lee, Seulbi, et al.
Pubblicazione: (2026)

Erasing with Precision: Evaluating Specific Concept Erasure from Text-to-Image Generative Models
di: Fuchi, Masane, et al.
Pubblicazione: (2025)

FlipConcept: Tuning-Free Multi-Concept Personalization for Text-to-Image Generation
di: Woo, Young Beom, et al.
Pubblicazione: (2025)

DyME: Dynamic Multi-Concept Erasure in Diffusion Models with Bi-Level Orthogonal LoRA Adaptation
di: Liu, Jiaqi, et al.
Pubblicazione: (2025)

KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis
di: Lee, Youngwan, et al.
Pubblicazione: (2023)

Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Models
di: Kim, Hyungjin, et al.
Pubblicazione: (2025)

Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion
di: Kim, Sanghyun, et al.
Pubblicazione: (2024)

CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
di: Jiang, Dongzhi, et al.
Pubblicazione: (2024)

Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models
di: Shi, Zhuan, et al.
Pubblicazione: (2026)

Local Representative Token Guided Merging for Text-to-Image Generation
di: Lee, Min-Jeong, et al.
Pubblicazione: (2025)

Semantic Guidance Tuning for Text-To-Image Diffusion Models
di: Kang, Hyun, et al.
Pubblicazione: (2023)

Editing Massive Concepts in Text-to-Image Diffusion Models
di: Xiong, Tianwei, et al.
Pubblicazione: (2024)

Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models
di: Gong, Chao, et al.
Pubblicazione: (2024)

Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models
di: Jang, Sangwon, et al.
Pubblicazione: (2024)

DiffExp: Efficient Exploration in Reward Fine-tuning for Text-to-Image Diffusion Models
di: Chae, Daewon, et al.
Pubblicazione: (2025)

CGCE: Classifier-Guided Concept Erasure in Generative Models
di: Nguyen, Viet, et al.
Pubblicazione: (2025)

CIPHER: Counterfeit Image Pattern High-level Examination via Representation
di: Kim, Kyeonghun, et al.
Pubblicazione: (2026)

Text-Aware Image Restoration with Diffusion Models
di: Min, Jaewon, et al.
Pubblicazione: (2025)

Grounding Text-to-Image Diffusion Models for Controlled High-Quality Image Generation
di: Süleyman, Ahmad, et al.
Pubblicazione: (2025)

GrOCE:Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models
di: Han, Ning, et al.
Pubblicazione: (2025)

InpDiffusion: Image Inpainting Localization via Conditional Diffusion Models
di: Wang, Kai, et al.
Pubblicazione: (2025)

GLYPH-SR: Can We Achieve Both High-Quality Image Super-Resolution and High-Fidelity Text Recovery via VLM-guided Latent Diffusion Model?
di: Sung, Mingyu, et al.
Pubblicazione: (2025)