Imagen de Portada

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhao, Kairan, Triantafillou, Eleni, Triantafillou, Peter
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Benchmarking Unlearning for Vision Transformers
por: Zhao, Kairan, et al.
Publicado: (2026)

Don't Deceive Me: Mitigating Gaslighting through Attention Reallocation in LMMs
por: Jiao, Pengkun, et al.
Publicado: (2025)

Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models
por: Yu, Lu, et al.
Publicado: (2024)

Vision Transformers Don't Need Trained Registers
por: Jiang, Nick, et al.
Publicado: (2025)

Text is All You Need for Vision-Language Model Jailbreaking
por: Chen, Yihang, et al.
Publicado: (2026)

Image is All You Need to Empower Large-scale Diffusion Models for In-Domain Generation
por: Cao, Pu, et al.
Publicado: (2023)

Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis
por: Zhang, Letian, et al.
Publicado: (2025)

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
por: Siddiqui, Shoaib Ahmed, et al.
Publicado: (2025)

[MASK] is All You Need
por: Hu, Vincent Tao, et al.
Publicado: (2024)

Off-The-Shelf Image-to-Image Models Are All You Need To Defeat Image Protection Schemes
por: Pleimling, Xavier, et al.
Publicado: (2026)

When Text and Images Don't Mix: Bias-Correcting Language-Image Similarity Scores for Anomaly Detection
por: Goodge, Adam, et al.
Publicado: (2024)

Not All Attention Heads Are What You Need: Refining CLIP's Image Representation with Attention Ablation
por: Lin, Feng, et al.
Publicado: (2025)

Beta Sampling is All You Need: Efficient Image Generation Strategy for Diffusion Models using Stepwise Spectral Analysis
por: Lee, Haeil, et al.
Publicado: (2024)

Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models
por: Woo, Sangmin, et al.
Publicado: (2024)

Zoom and Shift are All You Need
por: Qin, Jiahao
Publicado: (2024)

Don't Play Favorites: Minority Guidance for Diffusion Models
por: Um, Soobin, et al.
Publicado: (2023)

CLIP is All You Need for Human-like Semantic Representations in Stable Diffusion
por: Braunstein, Cameron, et al.
Publicado: (2025)

MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selection
por: Dutt, Raman, et al.
Publicado: (2024)

Ideal Registration? Segmentation is All You Need
por: Chen, Xiang, 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)

Memory augment is All You Need for image restoration
por: Zhang, Xiao Feng, et al.
Publicado: (2023)

FineVision: Open Data Is All You Need
por: Wiedmann, Luis, et al.
Publicado: (2025)

AID: Attention Interpolation of Text-to-Image Diffusion
por: He, Qiyuan, et al.
Publicado: (2024)

To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models
por: Barbulescu, George-Octavian, et al.
Publicado: (2024)

Uncovering the Text Embedding in Text-to-Image Diffusion Models
por: Yu, Hu, et al.
Publicado: (2024)

Detecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-Probability
por: Asthana, Rohan, et al.
Publicado: (2026)

Focus, Don't Prune: Identifying Instruction-Relevant Regions for Information-Rich Image Understanding
por: Kwon, Mincheol, et al.
Publicado: (2026)

Demystifying Foreground-Background Memorization in Diffusion Models
por: Di, Jimmy Z., et al.
Publicado: (2025)

Don't Fear Peculiar Activation Functions: EUAF and Beyond
por: Wang, Qianchao, et al.
Publicado: (2024)

CopyJudge: Automated Copyright Infringement Identification and Mitigation in Text-to-Image Diffusion Models
por: Liu, Shunchang, et al.
Publicado: (2025)

Camouflaged Image Synthesis Is All You Need to Boost Camouflaged Detection
por: Zhang, Haichao, et al.
Publicado: (2023)

All You Need in Knowledge Distillation Is a Tailored Coordinate System
por: Zhou, Junjie, et al.
Publicado: (2024)

Rethinking Deep Clustering Paradigms: Self-Supervision Is All You Need
por: Shaheena, Amal, et al.
Publicado: (2025)

On Memorization in Diffusion Models
por: Gu, Xiangming, et al.
Publicado: (2023)

Render, Don't Decode: Weight-Space World Models with Latent Structural Disentanglement
por: Nzoyem, Roussel Desmond, et al.
Publicado: (2026)

Self-supervised Dataset Distillation: A Good Compression Is All You Need
por: Zhou, Muxin, et al.
Publicado: (2024)

Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need
por: Wang, Qiang, et al.
Publicado: (2025)

Anatomy Might Be All You Need: Forecasting What to Do During Surgery
por: Sarwin, Gary, et al.
Publicado: (2025)

Taxes Are All You Need: Integration of Taxonomical Hierarchy Relationships into the Contrastive Loss
por: Kokilepersaud, Kiran, et al.
Publicado: (2024)

Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion
por: Karnik, Sathwik, et al.
Publicado: (2026)