Cover Image

Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Hyeonjin, Jung, Hangyeol, Yun, Heechan, Yun, Sungjun, Han, Dong-Jun
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

No Alignment Needed for Generation: Learning Linearly Separable Representations in Diffusion Models
by: Yun, Junno, et al.
Published: (2025)

Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models
by: Jun, Youngjun, et al.
Published: (2024)

Post-Hoc Concept Disentanglement: From Correlated to Isolated Concept Representations
by: Erogullari, Eren, et al.
Published: (2025)

Generative Visual Code Mobile World Models
by: Koh, Woosung, et al.
Published: (2026)

ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
by: Lin, Shen, et al.
Published: (2026)

Scaffold Diffusion: Sparse Multi-Category Voxel Structure Generation with Discrete Diffusion
by: Jung, Justin
Published: (2025)

Rethinking Post-Unlearning Behavior of Large Vision-Language Models
by: Kim, Minsung, et al.
Published: (2025)

Symbolic Disentangled Representations for Images
by: Korchemnyi, Alexandr, et al.
Published: (2024)

Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers
by: Jun, Youngjun, et al.
Published: (2026)

DEAL: Disentangle and Localize Concept-level Explanations for VLMs
by: Li, Tang, et al.
Published: (2024)

Learning Equi-angular Representations for Online Continual Learning
by: Seo, Minhyuk, et al.
Published: (2024)

SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligence
by: Dubovik, Viktar, et al.
Published: (2025)

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

DreamMakeup: Face Makeup Customization using Latent Diffusion Models
by: Park, Geon Yeong, et al.
Published: (2025)

Improving Visual Representation Alignment Generation with GRPO
by: Mo, Shentong, et al.
Published: (2026)

Unsupervised Learning of Disentangled Representations from Video
by: Denton, Remi, et al.
Published: (2017)

Explicitly Disentangled Representations in Object-Centric Learning
by: Majellaro, Riccardo, et al.
Published: (2024)

Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation
by: Liu, Chenruo, et al.
Published: (2025)

Concept Arithmetics for Circumventing Concept Inhibition in Diffusion Models
by: Petsiuk, Vitali, et al.
Published: (2024)

Denoising Multi-Beta VAE: Representation Learning for Disentanglement and Generation
by: Uppal, Anshuk, et al.
Published: (2025)

Sequential Representation Learning via Static-Dynamic Conditional Disentanglement
by: Simon, Mathieu Cyrille, et al.
Published: (2024)

Can Diffusion Models Disentangle? A Theoretical Perspective
by: Wang, Liming, et al.
Published: (2025)

Don't Judge by the Look: Towards Motion Coherent Video Representation
by: Zhang, Yitian, et al.
Published: (2024)

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

VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations
by: Zargarbashi, Fatemeh, et al.
Published: (2026)

Prompt-Based Safety Guidance Is Ineffective for Unlearned Text-to-Image Diffusion Models
by: Shin, Jiwoo, et al.
Published: (2025)

ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning
by: Chavhan, Ruchika, et al.
Published: (2024)

REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models
by: Zou, Yong, et al.
Published: (2026)

Causality in Video Diffusers is Separable from Denoising
by: Bai, Xingjian, et al.
Published: (2026)

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

Pre-trained Vision-Language Models Learn Discoverable Visual Concepts
by: Zang, Yuan, et al.
Published: (2024)

i-MAE: Are Latent Representations in Masked Autoencoders Linearly Separable?
by: Zhang, Kevin, et al.
Published: (2022)

One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications
by: Lyu, Mengyao, et al.
Published: (2023)

Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers
by: Chen, Pengtao, et al.
Published: (2025)

Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability
by: Mikriukov, Georgii, et al.
Published: (2023)

Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models
by: Ren, Qihan, et al.
Published: (2023)

DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning
by: Bai, Sikai, et al.
Published: (2024)

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

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates
by: Ahn, Jaewoo, et al.
Published: (2025)