Imagen de Portada

Now You See It, Now You Don't - Instant Concept Erasure for Safe Text-to-Image and Video Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Biswas, Shristi Das, Roy, Arani, Roy, Kaushik
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Now You See Me, Now You Don't: A Unified Framework for Expression Consistent Anonymization in Talking Head Videos
por: Egin, Anil, et al.
Publicado: (2026)

HEART: Hyperspherical Embedding Alignment via Kent-Representation Traversal in Diffusion Models
por: Roy, Arani, et al.
Publicado: (2026)

Towards Scalable Modeling of Compressed Videos for Efficient Action Recognition
por: Biswas, Shristi Das, et al.
Publicado: (2025)

SlimDiff: Training-Free, Activation-Guided Hands-free Slimming of Diffusion Models
por: Roy, Arani, et al.
Publicado: (2025)

Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning
por: Roy, Arani, et al.
Publicado: (2025)

MAGIC: Multimodal Alignment & Grounding-aware Instruction Coreset for Vision-Language Models
por: Biswas, Shristi Das, et al.
Publicado: (2026)

NowYouSee Me: Context-Aware Automatic Audio Description
por: Lee, Seon-Ho, et al.
Publicado: (2024)

PIXELS: Progressive Image Xemplar-based Editing with Latent Surgery
por: Biswas, Shristi Das, et al.
Publicado: (2025)

Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models
por: Li, Senmao, et al.
Publicado: (2024)

NeIn: Telling What You Don't Want
por: Bui, Nhat-Tan, et al.
Publicado: (2024)

Visually Dehallucinative Instruction Generation: Know What You Don't Know
por: Cha, Sungguk, et al.
Publicado: (2024)

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models
por: Zhao, Kairan, et al.
Publicado: (2026)

See It Before You Grab It: Deep Learning-based Action Anticipation in Basketball
por: Roy, Arnau Barrera, et al.
Publicado: (2025)

Your Robot Will Feel You Now: Empathy in Robots and Embodied Agents
por: Lim, Angelica, et al.
Publicado: (2026)

Do You See What I Am Pointing At? Gesture-Based Egocentric Video Question Answering
por: Choi, Yura, et al.
Publicado: (2026)

Don't Judge Before You CLIP: A Unified Approach for Perceptual Tasks
por: Zalcher, Amit, et al.
Publicado: (2025)

Is What You Ask For What You Get? Investigating Concept Associations in Text-to-Image Models
por: Magid, Salma Abdel, et al.
Publicado: (2024)

Now You See It, Now You Don't: Laryngoscopy Findings of Paradoxical Vocal Fold Motion
por: William Strober, et al.
Publicado: (2025)

You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale
por: Ma, Baorui, et al.
Publicado: (2024)

ACE: Anti-Editing Concept Erasure in Text-to-Image Models
por: Wang, Zihao, et al.
Publicado: (2025)

Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models
por: Gong, Chao, et al.
Publicado: (2024)

Edit as You See: Image-guided Video Editing via Masked Motion Modeling
por: Huang, Zhi-Lin, et al.
Publicado: (2025)

GrOCE:Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models
por: Han, Ning, et al.
Publicado: (2025)

Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models
por: Xie, Yiwei, et al.
Publicado: (2026)

If At First You Don't Succeed: Test Time Re-ranking for Zero-shot, Cross-domain Retrieval
por: Hudson, Finlay G. C., et al.
Publicado: (2023)

In Response to Now You See It, Now You Don't: Laryngoscopy Findings of Paradoxical Vocal Fold Motion
por: William Strober, et al.
Publicado: (2025)

You Only Speak Once to See
por: Yang, Wenhao, et al.
Publicado: (2024)

Comprehensive Evaluation and Analysis for NSFW Concept Erasure in Text-to-Image Diffusion Models
por: Chen, Die, et al.
Publicado: (2025)

The More You See in 2D, the More You Perceive in 3D
por: Han, Xinyang, et al.
Publicado: (2024)

VideoEraser: Concept Erasure in Text-to-Video Diffusion Models
por: Xu, Naen, et al.
Publicado: (2025)

To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now
por: Zhang, Yimeng, et al.
Publicado: (2023)

Tell What You Hear From What You See -- Video to Audio Generation Through Text
por: Liu, Xiulong, et al.
Publicado: (2024)

You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning
por: Moutakanni, Théo, et al.
Publicado: (2024)

Now you see it, Now you don't: Damage Label Agreement in Drone & Satellite Post-Disaster Imagery
por: Manzini, Thomas, et al.
Publicado: (2025)

You Think, You ACT: The New Task of Arbitrary Text to Motion Generation
por: Wang, Runqi, et al.
Publicado: (2024)

Can You Trust What You See? Alpha Channel No-Box Attacks on Video Object Detection
por: Yi, Ariana, et al.
Publicado: (2025)

Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration
por: Li, Jun, et al.
Publicado: (2026)

A Single Neuron Works: Precise Concept Erasure in Text-to-Image Diffusion Models
por: He, Qinqin, et al.
Publicado: (2025)

Show, Don't Tell: Morphing Latent Reasoning into Image Generation
por: Chen, Harold Haodong, et al.
Publicado: (2026)