Cover Image

Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ko, Junseok, Kim, Jungwoo, Lee, Jong-Seok
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation Misdirection
by: Lee, Uichan, et al.
Published: (2026)

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

EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectors
by: Kim, Sangwon, et al.
Published: (2024)

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

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

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

EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimization
by: Fan, Zhaoxin, et al.
Published: (2026)

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

Adaptive Explicit Knowledge Transfer for Knowledge Distillation
by: Park, Hyungkeun, et al.
Published: (2024)

How to Blend Concepts in Diffusion Models
by: Olearo, Lorenzo, et al.
Published: (2024)

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

TalkMosaic: Interactive PhotoMosaic with Multi-modal LLM Q&A Interactions
by: Li, Kevin, et al.
Published: (2024)

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

TraSCE: Trajectory Steering for Concept Erasure
by: Jain, Anubhav, et al.
Published: (2024)

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

OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure
by: Shi, Chuancheng, et al.
Published: (2026)

Plug-and-Play Multi-Concept Adaptive Blending for High-Fidelity Text-to-Image Synthesis
by: Woo, Young-Beom
Published: (2025)

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

Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters
by: Wang, Yuan, et al.
Published: (2024)

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

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

CD-FKD: Cross-Domain Feature Knowledge Distillation for Robust Single-Domain Generalization in Object Detection
by: Lee, Junseok, et al.
Published: (2026)

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

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

Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency
by: Kim, Hyeongjin, et al.
Published: (2024)

Cached Multi-Lora Composition for Multi-Concept Image Generation
by: Zou, Xiandong, et al.
Published: (2025)

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

Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization
by: Lan, Yuqin, et al.
Published: (2026)

Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models
by: Lee, Tae-Young, et al.
Published: (2025)

MF-LPR$^2$: Multi-Frame License Plate Image Restoration and Recognition using Optical Flow
by: Na, Kihyun, et al.
Published: (2025)

CoBELa: Steering Transparent Generation via Concept Bottlenecks on Energy Landscapes
by: Kim, Sangwon, et al.
Published: (2025)

MotionCFG: Boosting Motion Dynamics via Stochastic Concept Perturbation
by: Kim, Byungjun, et al.
Published: (2026)

Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models
by: Kwon, Gihyun, et al.
Published: (2024)

Ordering Matters: Rank-Aware Selective Fusion for Blended Emotion Recognition
by: Lee, Junghyun, et al.
Published: (2026)

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

SYNTHIA: Novel Concept Design with Affordance Composition
by: Ha, Hyeonjeong, et al.
Published: (2025)

Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition
by: Yeh, Chun-Hsiao, et al.
Published: (2024)

Imagine for Me: Creative Conceptual Blending of Real Images and Text via Blended Attention
by: Cho, Wonwoong, et al.
Published: (2025)

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

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