Copertina

ConceptPrism: Concept Disentanglement in Personalized Diffusion Models via Residual Token Optimization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kim, Minseo, Kwon, Minchan, Lee, Dongyeun, Jeon, Yunho, Kim, Junmo
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Comparison Reveals Commonality: Customized Image Generation through Contrastive Inversion
di: Kim, Minseo, et al.
Pubblicazione: (2025)

MDS-DETR: DETR with Masked Duplicate Suppressor
di: Lee, Chanho, et al.
Pubblicazione: (2026)

Learning Question-Aware Keyframe Selection with Synthetic Supervision for Video Question Answering
di: Kwon, Minchan, et al.
Pubblicazione: (2026)

ConceptSplit: Decoupled Multi-Concept Personalization of Diffusion Models via Token-wise Adaptation and Attention Disentanglement
di: Lim, Habin, et al.
Pubblicazione: (2025)

Inlier-Centric Post-Training Quantization for Object Detection Models
di: Kim, Minsu, et al.
Pubblicazione: (2026)

DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization
di: Lee, Dongyeun, et al.
Pubblicazione: (2025)

Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
di: Hur, Jiwan, et al.
Pubblicazione: (2024)

FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection
di: Lee, Chanho, et al.
Pubblicazione: (2023)

DiCo: Disentangled Concept Representation for Text-to-image Person Re-identification
di: Kim, Giyeol, et al.
Pubblicazione: (2026)

SFLD: Reducing the content bias for AI-generated Image Detection
di: Gye, Seoyeon, et al.
Pubblicazione: (2025)

Locality-aware Concept Bottleneck Model
di: Jeon, Sujin, et al.
Pubblicazione: (2025)

OmniPrism: Learning Disentangled Visual Concept for Image Generation
di: Li, Yangyang, et al.
Pubblicazione: (2024)

Instruct-4DGS: Efficient Dynamic Scene Editing via 4D Gaussian-based Static-Dynamic Separation
di: Kwon, Joohyun, et al.
Pubblicazione: (2025)

Beyond Semantics: Disentangling Information Scope in Sparse Autoencoders for CLIP
di: Ro, Yusung, et al.
Pubblicazione: (2026)

Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition
di: Lee, Jongseo, et al.
Pubblicazione: (2025)

IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models
di: Lee, Dong-Jae, et al.
Pubblicazione: (2026)

Personalized Residuals for Concept-Driven Text-to-Image Generation
di: Ham, Cusuh, et al.
Pubblicazione: (2024)

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

Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gate
di: Lee, Byung Hyun, et al.
Pubblicazione: (2025)

ConceptWeaver: Weaving Disentangled Concepts with Flow
di: Chen, Jintao, et al.
Pubblicazione: (2026)

Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
di: Kim, Hyeonjin, et al.
Pubblicazione: (2026)

UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens
di: An, Ruichuan, et al.
Pubblicazione: (2025)

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

Do Vision Models Encode Object-Level Semantic Relatedness? A Cognitive Psychology-Inspired Benchmark
di: Lee, Hansang, et al.
Pubblicazione: (2017)

Rethinking Token Reduction for Diffusion Models via Output-Similarity-Awareness
di: Lee, Hangyeol, et al.
Pubblicazione: (2026)

Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models
di: Moon, Saemi, et al.
Pubblicazione: (2026)

PROBE: Diagnosing Residual Concept Capacity in Erased Text-to-Video Diffusion Models
di: Xie, Yiwei, et al.
Pubblicazione: (2026)

Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision Localization
di: Zhang, Lingyun, et al.
Pubblicazione: (2024)

ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts
di: Choi, Jinho, et al.
Pubblicazione: (2025)

Lego: Learning to Disentangle and Invert Personalized Concepts Beyond Object Appearance in Text-to-Image Diffusion Models
di: Motamed, Saman, et al.
Pubblicazione: (2023)

Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Models
di: Xie, Yan, et al.
Pubblicazione: (2025)

Beta Sampling is All You Need: Efficient Image Generation Strategy for Diffusion Models using Stepwise Spectral Analysis
di: Lee, Haeil, et al.
Pubblicazione: (2024)

Adversarial Concept Distillation for One-Step Diffusion Personalization
di: Yang, Yixiong, et al.
Pubblicazione: (2025)

Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient
di: Wu, Yongliang, et al.
Pubblicazione: (2024)

CusConcept: Customized Visual Concept Decomposition with Diffusion Models
di: Xu, Zhi, et al.
Pubblicazione: (2024)

Modeling Stereo-Confidence Out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep
di: Lee, Jae Young, et al.
Pubblicazione: (2024)

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

Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models
di: Jin, Hyundong, et al.
Pubblicazione: (2026)

Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations
di: Kwon, Dahee, et al.
Pubblicazione: (2025)

Grid Diffusion Models for Text-to-Video Generation
di: Lee, Taegyeong, et al.
Pubblicazione: (2024)