Imagen de Portada

ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Guo, Zirun, Jin, Tao
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Smoothing the Shift: Towards Stable Test-Time Adaptation under Complex Multimodal Noises
por: Guo, Zirun, et al.
Publicado: (2025)

ConceptGuard: Proactive Safety in Text-and-Image-to-Video Generation through Multimodal Risk Detection
por: Ma, Ruize, et al.
Publicado: (2025)

Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Models
por: Lai, Songning, et al.
Publicado: (2024)

Efficient Prompting for Continual Adaptation to Missing Modalities
por: Guo, Zirun, et al.
Publicado: (2025)

LLM-I: LLMs are Naturally Interleaved Multimodal Creators
por: Guo, Zirun, et al.
Publicado: (2025)

A Wander Through the Multimodal Landscape: Efficient Transfer Learning via Low-rank Sequence Multimodal Adapter
por: Guo, Zirun, et al.
Publicado: (2024)

Observe-R1: Unlocking Reasoning Abilities of MLLMs with Dynamic Progressive Reinforcement Learning
por: Guo, Zirun, et al.
Publicado: (2025)

Classifier-guided Gradient Modulation for Enhanced Multimodal Learning
por: Guo, Zirun, et al.
Publicado: (2024)

Mitigating Catastrophic Forgetting and Mode Collapse in Text-to-Image Diffusion via Latent Replay
por: Otani, Aoi
Publicado: (2025)

Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models
por: Deng, Kaiyuan, et al.
Publicado: (2026)

AlignGuard: Scalable Safety Alignment for Text-to-Image Generation
por: Liu, Runtao, et al.
Publicado: (2024)

More Than Memory Savings: Zeroth-Order Optimization Mitigates Forgetting in Continual Learning
por: Yu, Wanhao, et al.
Publicado: (2025)

Directional Textual Inversion for Personalized Text-to-Image Generation
por: Kim, Kunhee, et al.
Publicado: (2025)

Forget Less by Learning Together through Concept Consolidation
por: Kaushik, Arjun Ramesh, et al.
Publicado: (2026)

Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
por: Deng, Kaiyuan, et al.
Publicado: (2026)

SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation
por: Yoon, Jaehong, et al.
Publicado: (2024)

Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
por: Lou, Meng, et al.
Publicado: (2026)

Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin
por: Wang, Yuchen, et al.
Publicado: (2025)

Anti-Forgetting Adaptation for Unsupervised Person Re-identification
por: Chen, Hao, et al.
Publicado: (2024)

Mitigating Bias in Concept Bottleneck Models for Fair and Interpretable Image Classification
por: Tong, Schrasing, et al.
Publicado: (2026)

ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval
por: Xing, Eric, et al.
Publicado: (2025)

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

Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive Replay
por: Rezaei, Hossein, et al.
Publicado: (2024)

Progressive Compositionality in Text-to-Image Generative Models
por: Han, Evans Xu, et al.
Publicado: (2024)

Latent Guard: a Safety Framework for Text-to-image Generation
por: Liu, Runtao, et al.
Publicado: (2024)

Steering Guidance for Personalized Text-to-Image Diffusion Models
por: Park, Sunghyun, et al.
Publicado: (2025)

Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimization
por: Li, Gen, et al.
Publicado: (2025)

GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping
por: Wang, Jing, et al.
Publicado: (2025)

DriftGuard: A Hierarchical Framework for Concept Drift Detection and Remediation in Supply Chain Forecasting
por: Alam, Shahnawaz, et al.
Publicado: (2026)

APO: Enhancing Reasoning Ability of MLLMs via Asymmetric Policy Optimization
por: Hong, Minjie, et al.
Publicado: (2025)

BiasMap: Leveraging Cross-Attentions to Discover and Mitigate Hidden Social Biases in Text-to-Image Generation
por: Chakraborty, Rajatsubhra, et al.
Publicado: (2025)

Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting
por: Liu, Yuyang, et al.
Publicado: (2025)

Continual Learning of Achieving Forgetting-free and Positive Knowledge Transfer
por: Wang, Zhi, et al.
Publicado: (2026)

Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting
por: Hess, Timm, et al.
Publicado: (2023)

Preventing Catastrophic Forgetting through Memory Networks in Continuous Detection
por: Bhatt, Gaurav, et al.
Publicado: (2024)

Robust Continual Unlearning against Knowledge Erosion and Forgetting Reversal
por: Park, Eun-Ju, et al.
Publicado: (2026)

Assessing Open-world Forgetting in Generative Image Model Customization
por: Laria, Héctor, et al.
Publicado: (2024)

DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation
por: Jiang, Dongzhi, et al.
Publicado: (2025)

ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models
por: Patel, Maitreya, et al.
Publicado: (2023)

ReText: Text Boosts Generalization in Image-Based Person Re-identification
por: Mamedov, Timur, et al.
Publicado: (2026)