Cover Image

Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jin, Hyundong, Han, Dongyoon, Kim, Eunwoo
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models
by: Jin, Hyundong, et al.
Published: (2025)

Continual Learning for Multiple Modalities
by: Jin, Hyundong, et al.
Published: (2025)

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

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

SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders
by: Li, Qing, et al.
Published: (2025)

Erase Persona, Forget Lore: Benchmarking Multimodal Copyright Unlearning in Large Vision Language Models
by: Kwon, JuneHyoung, et al.
Published: (2026)

Improving Concept Alignment in Vision-Language Concept Bottleneck Models
by: Selvaraj, Nithish Muthuchamy, et al.
Published: (2024)

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning
by: Tan, Zhangyun, et al.
Published: (2026)

ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation
by: Guo, Zirun, et al.
Published: (2025)

AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models
by: Chen, Haokun, et al.
Published: (2025)

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

Language Guided Concept Bottleneck Models for Interpretable Continual Learning
by: Yu, Lu, et al.
Published: (2025)

Stake the Points: Structure-Faithful Instance Unlearning
by: Hong, Kiseong, et al.
Published: (2026)

Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models
by: Kim, Jeonghwan, et al.
Published: (2024)

Concept Unlearning by Modeling Key Steps of Diffusion Process
by: Zhang, Chaoshuo, et al.
Published: (2025)

VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models
by: Ranjan, Ravi, et al.
Published: (2026)

Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation
by: Han, Su Ho, et al.
Published: (2025)

D-Attn: Decomposed Attention for Large Vision-and-Language Models
by: Kuo, Chia-Wen, et al.
Published: (2025)

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

CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models
by: Biswas, Shristi Das, et al.
Published: (2025)

Learning with Unmasked Tokens Drives Stronger Vision Learners
by: Kim, Taekyung, et al.
Published: (2023)

Continual Forgetting for Pre-trained Vision Models
by: Zhao, Hongbo, et al.
Published: (2024)

Concept-Guided Prompt Learning for Generalization in Vision-Language Models
by: Zhang, Yi, et al.
Published: (2024)

Human Preference-Aligned Concept Customization Benchmark via Decomposed Evaluation
by: Ishikawa, Reina, et al.
Published: (2025)

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

Unlearning Concepts from Text-to-Video Diffusion Models
by: Liu, Shiqi, et al.
Published: (2024)

Continuous Concepts Removal in Text-to-image Diffusion Models
by: Han, Tingxu, et al.
Published: (2024)

Morphing Tokens Draw Strong Masked Image Models
by: Kim, Taekyung, et al.
Published: (2023)

Beyond CLIP Generalization: Against Forward&Backward Forgetting Adapter for Continual Learning of Vision-Language Models
by: Dong, Songlin, et al.
Published: (2025)

Video Unlearning via Low-Rank Refusal Vector
by: Facchiano, Simone, et al.
Published: (2025)

Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges
by: Sapkota, Ranjan, et al.
Published: (2025)

Concept-skill Transferability-based Data Selection for Large Vision-Language Models
by: Lee, Jaewoo, et al.
Published: (2024)

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts
by: Gao, Hongcheng, et al.
Published: (2024)

Dual-Modality Anchor-Guided Filtering for Test-time Prompt Tuning
by: Choi, Jungwon, et al.
Published: (2026)

Designing to Forget: Deep Semi-parametric Models for Unlearning
by: Zheng, Amber Yijia, et al.
Published: (2026)

ConceptPrism: Concept Disentanglement in Personalized Diffusion Models via Residual Token Optimization
by: Kim, Minseo, et al.
Published: (2026)

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

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

To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models
by: Tian, Bozhong, et al.
Published: (2024)

Concept Retrieval -- What and How?
by: Nizan, Ori, et al.
Published: (2025)