Copertina

Concept Arithmetics for Circumventing Concept Inhibition in Diffusion Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Petsiuk, Vitali, Saenko, Kate
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

GoldiCLIP: The Goldilocks Approach for Balancing Explicit Supervision for Language-Image Pretraining
di: Mohan, Deen Dayal, et al.
Pubblicazione: (2026)

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

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

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

Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models
di: Singhi, Nishad, et al.
Pubblicazione: (2024)

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

Prompt Optimizer of Text-to-Image Diffusion Models for Abstract Concept Understanding
di: Fan, Zezhong, et al.
Pubblicazione: (2024)

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

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

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

Editable Concept Bottleneck Models
di: Hu, Lijie, et al.
Pubblicazione: (2024)

Contrastive CFG: Improving CFG in Diffusion Models by Contrasting Positive and Negative Concepts
di: Chang, Jinho, et al.
Pubblicazione: (2024)

Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations
di: Xu, Xinyue, et al.
Pubblicazione: (2024)

A Geometric Unification of Concept Learning with Concept Cones
di: Rocchi--Henry, Alexandre, et al.
Pubblicazione: (2025)

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

Semi-supervised Concept Bottleneck Models
di: Hu, Lijie, et al.
Pubblicazione: (2024)

Understanding Visual Concepts Across Models
di: Trabucco, Brandon, et al.
Pubblicazione: (2024)

Zero-shot Concept Bottleneck Models
di: Yamaguchi, Shin'ya, et al.
Pubblicazione: (2025)

Process-Guided Concept Bottleneck Model
di: Asiyabi, Reza M., et al.
Pubblicazione: (2026)

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

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

OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models
di: Aliev, Ali, et al.
Pubblicazione: (2026)

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

Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery
di: Rao, Sukrut, et al.
Pubblicazione: (2024)

Locally Testing Model Detections for Semantic Global Concepts
di: Motzkus, Franz, et al.
Pubblicazione: (2024)

CFM: Language-aligned Concept Foundation Model for Vision
di: Wittenmayer, Kai, et al.
Pubblicazione: (2026)

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

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

Restyling Unsupervised Concept Based Interpretable Networks with Generative Models
di: Parekh, Jayneel, et al.
Pubblicazione: (2024)

Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts
di: Choi, Jihye, et al.
Pubblicazione: (2024)

Concept-Based Unsupervised Domain Adaptation
di: Xu, Xinyue, et al.
Pubblicazione: (2025)

What Lurks Within? Concept Auditing for Shared Diffusion Models at Scale
di: Yuan, Xiaoyong, et al.
Pubblicazione: (2025)

Achieving Data Efficient Neural Networks with Hybrid Concept-based Models
di: Opsahl, Tobias A., et al.
Pubblicazione: (2024)

Walking the Web of Concept-Class Relationships in Incrementally Trained Interpretable Models
di: Agrawal, Susmit, et al.
Pubblicazione: (2025)

Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance
di: Park, Dongmin, et al.
Pubblicazione: (2024)

Concept Matching with Agent for Out-of-Distribution Detection
di: Lee, Yuxiao, et al.
Pubblicazione: (2024)

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

Concept-Guided Interpretability via Neural Chunking
di: Wu, Shuchen, et al.
Pubblicazione: (2025)

Measuring the (Un)Faithfulness of Concept-Based Explanations
di: Kumar, Shubham, et al.
Pubblicazione: (2025)