Cover Image

Memorization In Stable Diffusion Is Unexpectedly Driven by CLIP Embeddings

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Bumjun, No, Albert
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Captured by Captions: On Memorization and its Mitigation in CLIP Models
by: Wang, Wenhao, et al.
Published: (2025)

On Memorization in Diffusion Models
by: Gu, Xiangming, et al.
Published: (2023)

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

CLIP Can Understand Depth
by: Kim, Sohee, et al.
Published: (2024)

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

Memorized Images in Diffusion Models share a Subspace that can be Located and Deleted
by: Chavhan, Ruchika, et al.
Published: (2024)

Enhancing CLIP Conceptual Embedding through Knowledge Distillation
by: Kao, Kuei-Chun
Published: (2024)

Impact of Layer Norm on Memorization and Generalization in Transformers
by: Singhal, Rishi, et al.
Published: (2025)

DiffCLIP: Differential Attention Meets CLIP
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2025)

Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
by: Schlarmann, Christian, et al.
Published: (2024)

CountCLIP -- [Re] Teaching CLIP to Count to Ten
by: Mestha, Harshvardhan, et al.
Published: (2024)

Reproducibility Study of CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification
by: Shah, Manan, et al.
Published: (2024)

SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery
by: Klemmer, Konstantin, et al.
Published: (2023)

Test-Time Alignment of Text-to-Image Diffusion Models via Null-Text Embedding Optimisation
by: Kim, Taehoon, et al.
Published: (2025)

Advancing AI-Powered Medical Image Synthesis: Insights from MedVQA-GI Challenge Using CLIP, Fine-Tuned Stable Diffusion, and Dream-Booth + LoRA
by: Peter, Ojonugwa Oluwafemi Ejiga, et al.
Published: (2025)

VeCLIP: Improving CLIP Training via Visual-enriched Captions
by: Lai, Zhengfeng, et al.
Published: (2023)

SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2024)

Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection
by: Guille-Escuret, Charles, et al.
Published: (2023)

Fine-tuning CLIP Text Encoders with Two-step Paraphrasing
by: Kim, Hyunjae, et al.
Published: (2024)

CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation
by: Zhou, Chenliang, et al.
Published: (2022)

CellCLIP -- Learning Perturbation Effects in Cell Painting via Text-Guided Contrastive Learning
by: Lu, Mingyu, et al.
Published: (2025)

What to Do Next? Memorizing skills from Egocentric Instructional Video
by: Bi, Jing, et al.
Published: (2025)

Classifier-Free Guidance inside the Attraction Basin May Cause Memorization
by: Jain, Anubhav, et al.
Published: (2024)

ECOR: Explainable CLIP for Object Recognition
by: Rasekh, Ali, et al.
Published: (2024)

Interpreting CLIP with Hierarchical Sparse Autoencoders
by: Zaigrajew, Vladimir, et al.
Published: (2025)

Implicit Inversion turns CLIP into a Decoder
by: D'Orazio, Antonio, et al.
Published: (2025)

Steering CLIP's vision transformer with sparse autoencoders
by: Joseph, Sonia, et al.
Published: (2025)

IDEA: Image Description Enhanced CLIP-Adapter
by: Ye, Zhipeng, et al.
Published: (2025)

Stable Diffusion Dataset Generation for Downstream Classification Tasks
by: Lomurno, Eugenio, et al.
Published: (2024)

The Disappearance of Timestep Embedding in Modern Time-Dependent Neural Networks
by: Kim, Bum Jun, et al.
Published: (2024)

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
by: Chu, Tianzhe, et al.
Published: (2025)

Configuring Data Augmentations to Reduce Variance Shift in Positional Embedding of Vision Transformers
by: Kim, Bum Jun, et al.
Published: (2024)

WalkCLIP: Multimodal Learning for Urban Walkability Prediction
by: Xiang, Shilong, et al.
Published: (2025)

Learning Generalizable Prompt for CLIP with Class Similarity Knowledge
by: Jung, Sehun, et al.
Published: (2025)

RankCLIP: Ranking-Consistent Language-Image Pretraining
by: Zhang, Yiming, et al.
Published: (2024)

CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP
by: Yang, Tianyu, et al.
Published: (2024)

Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs
by: Lou, Siyu, et al.
Published: (2024)

On the Reproducibility of "FairCLIP: Harnessing Fairness in Vision-Language Learning''
by: Bakker, Hua Chang, et al.
Published: (2025)

Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts
by: Crabbé, Jonathan, et al.
Published: (2023)

Controlling Latent Diffusion Using Latent CLIP
by: Becker, Jason, et al.
Published: (2025)