Copertina

Broken Memories: Detecting and Mitigating Memorization in Diffusion Models with Degraded Generations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Huang, Yuanmin, Zhang, Mi, Chen, Chen, Li, Feifei, Hong, Geng, You, Xiaoyu, Yang, Min
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SafeRoPE: Risk-specific Head-wise Embedding Rotation for Safe Generation in Rectified Flow Transformers
di: Yang, Xiang, et al.
Pubblicazione: (2026)

Detecting, Explaining, and Mitigating Memorization in Diffusion Models
di: Wen, Yuxin, et al.
Pubblicazione: (2024)

SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse
di: Sun, Yiming, et al.
Pubblicazione: (2025)

3D-ANC: Adaptive Neural Collapse for Robust 3D Point Cloud Recognition
di: Huang, Yuanmin, et al.
Pubblicazione: (2025)

Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization
di: Li, Feifei, et al.
Pubblicazione: (2025)

Redistribute Ensemble Training for Mitigating Memorization in Diffusion Models
di: Guan, Xiaoliu, et al.
Pubblicazione: (2025)

Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models
di: Chen, Chen, et al.
Pubblicazione: (2025)

Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models
di: Han, Hyeonggeun, et al.
Pubblicazione: (2025)

Towards Memorization-Free Diffusion Models
di: Chen, Chen, et al.
Pubblicazione: (2024)

Investigating Memorization in Video Diffusion Models
di: Chen, Chen, et al.
Pubblicazione: (2024)

Mitigating Memorization in Text-to-Image Diffusion via Region-Aware Prompt Augmentation and Multimodal Copy Detection
di: Chen, Yunzhuo, et al.
Pubblicazione: (2026)

Unconsciously Forget: Mitigating Memorization; Without Knowing What is being Memorized
di: Jin, Er, et al.
Pubblicazione: (2025)

Filtering Memorization from Parameter-Space in Diffusion Models
di: Zhe, Yu, et al.
Pubblicazione: (2026)

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

Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning
di: Gou, Yunhao, et al.
Pubblicazione: (2025)

On Memorization in Diffusion Models
di: Gu, Xiangming, et al.
Pubblicazione: (2023)

Capacity Control is an Effective Memorization Mitigation Mechanism in Text-Conditional Diffusion Models
di: Dutt, Raman, et al.
Pubblicazione: (2024)

Iterative Ensemble Training with Anti-Gradient Control for Mitigating Memorization in Diffusion Models
di: Liu, Xiao, et al.
Pubblicazione: (2024)

Exploring Local Memorization in Diffusion Models via Bright Ending Attention
di: Chen, Chen, et al.
Pubblicazione: (2024)

An Inversion-based Measure of Memorization for Diffusion Models
di: Ma, Zhe, et al.
Pubblicazione: (2024)

How Diffusion Models Memorize
di: Kim, Juyeop, et al.
Pubblicazione: (2025)

Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention
di: Ren, Jie, et al.
Pubblicazione: (2024)

MemBench: Memorized Image Trigger Prompt Dataset for Diffusion Models
di: Hong, Chunsan, et al.
Pubblicazione: (2024)

Face Swap via Diffusion Model
di: Wang, Feifei
Pubblicazione: (2024)

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

LVLMs as inspectors: an agentic framework for category-level structural defect annotation
di: Jiang, Sheng, et al.
Pubblicazione: (2025)

IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models
di: Yang, Jiabing, et al.
Pubblicazione: (2025)

Diffusion-Based Restoration for Multi-Modal 3D Object Detection in Adverse Weather
di: He, Zhijian, et al.
Pubblicazione: (2025)

Memorization to Generalization: Emergence of Diffusion Models from Associative Memory
di: Pham, Bao, et al.
Pubblicazione: (2025)

Ray-Aware Pointer Memory with Adaptive Updates for Streaming 3D Reconstruction
di: Li, Feifei, et al.
Pubblicazione: (2026)

Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation
di: Guo, Yanjun, et al.
Pubblicazione: (2026)

Unsupervised Fingerphoto Presentation Attack Detection With Diffusion Models
di: Li, Hailin, et al.
Pubblicazione: (2024)

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

Mitigate Replication and Copying in Diffusion Models with Generalized Caption and Dual Fusion Enhancement
di: Li, Chenghao, et al.
Pubblicazione: (2023)

YARD: Y-Architecture Register Decoding for Efficient Hallucination Mitigation in Large Vision-Language Models
di: Chen, Ting, et al.
Pubblicazione: (2026)

Generalized Visual Relation Detection with Diffusion Models
di: Gao, Kaifeng, et al.
Pubblicazione: (2025)

GR-Diffusion: 3D Gaussian Representation Meets Diffusion in Whole-Body PET Reconstruction
di: Geng, Mengxiao, et al.
Pubblicazione: (2026)

4DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation
di: Yang, Shuzhou, et al.
Pubblicazione: (2025)

Embedding Space Selection for Detecting Memorization and Fingerprinting in Generative Models
di: He, Jack, et al.
Pubblicazione: (2024)

Degradation-Modeled Multipath Diffusion for Tunable Metalens Photography
di: Zhang, Jianing, et al.
Pubblicazione: (2025)