Image de couverture de livre

What do we learn from inverting CLIP models?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kazemi, Hamid, Chegini, Atoosa, Geiping, Jonas, Feizi, Soheil, Goldstein, Tom
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning
par: Chegini, Atoosa, et autres
Publié: (2026)

Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP
par: Balasubramanian, Sriram, et autres
Publié: (2024)

Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion
par: Souri, Hossein, et autres
Publié: (2024)

Measuring Style Similarity in Diffusion Models
par: Somepalli, Gowthami, et autres
Publié: (2024)

Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
par: Saberi, Mehrdad, et autres
Publié: (2023)

How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings
par: Audia, Samuel, et autres
Publié: (2025)

RePanda: Pandas-powered Tabular Verification and Reasoning
par: Chegini, Atoosa Malemir, et autres
Publié: (2025)

A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
par: Kazemi, Hamid, et autres
Publié: (2026)

Is CLIP ideal? No. Can we fix it? Yes!
par: Kang, Raphi, et autres
Publié: (2025)

SpurLens: Automatic Detection of Spurious Cues in Multimodal LLMs
par: Hosseini, Parsa, et autres
Publié: (2025)

ECOR: Explainable CLIP for Object Recognition
par: Rasekh, Ali, et autres
Publié: (2024)

Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning
par: Kalibhat, Neha, et autres
Publié: (2024)

A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)
par: Tu, Weijie, et autres
Publié: (2024)

A Deep Bayesian Convolutional Spiking Neural Network-based CAD system with Uncertainty Quantification for Medical Images Classification
par: Chegini, Mohaddeseh, et autres
Publié: (2025)

Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP
par: Basu, Samyadeep, et autres
Publié: (2023)

What do vision-language models see in the context? Investigating multimodal in-context learning
par: Santos, Gabriel O. dos, et autres
Publié: (2025)

HyperCLIP: Adapting Vision-Language models with Hypernetworks
par: Akinwande, Victor, et autres
Publié: (2024)

DeCLIP: Decoding CLIP representations for deepfake localization
par: Smeu, Stefan, et autres
Publié: (2024)

IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment
par: Magistri, Simone, et autres
Publié: (2026)

Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning
par: Menghini, Cristina, et autres
Publié: (2023)

GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs
par: Parast, Aryan Yazdan, et autres
Publié: (2025)

FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs
par: Dehdashtian, Sepehr, et autres
Publié: (2024)

NeuCLIP: Efficient Large-Scale CLIP Training with Neural Normalizer Optimization
par: Wei, Xiyuan, et autres
Publié: (2025)

Extract Free Dense Misalignment from CLIP
par: Nam, JeongYeon, et autres
Publié: (2024)

FastCLIP: A Suite of Optimization Techniques to Accelerate CLIP Training with Limited Resources
par: Wei, Xiyuan, et autres
Publié: (2024)

Breaking the Limits of Open-Weight CLIP: An Optimization Framework for Self-supervised Fine-tuning of CLIP
par: Mehta, Anant, et autres
Publié: (2026)

CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling
par: Wang, Xinze, et autres
Publié: (2025)

MoP-CLIP: A Mixture of Prompt-Tuned CLIP Models for Domain Incremental Learning
par: Nicolas, Julien, et autres
Publié: (2023)

Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models
par: Shirkavand, Reza, et autres
Publié: (2024)

Quantifying Cross-Modality Memorization in Vision-Language Models
par: Wen, Yuxin, et autres
Publié: (2025)

Object Recognition as Next Token Prediction
par: Yue, Kaiyu, et autres
Publié: (2023)

TiC-CLIP: Continual Training of CLIP Models
par: Garg, Saurabh, et autres
Publié: (2023)

Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models
par: Moayeri, Mazda, et autres
Publié: (2024)

Online Zero-Shot Classification with CLIP
par: Qian, Qi, et autres
Publié: (2024)

MIP: CLIP-based Image Reconstruction from PEFT Gradients
par: Zhou, Peiheng, et autres
Publié: (2024)

Rethinking Artistic Copyright Infringements in the Era of Text-to-Image Generative Models
par: Moayeri, Mazda, et autres
Publié: (2024)

Finetuning CLIP to Reason about Pairwise Differences
par: Sam, Dylan, et autres
Publié: (2024)

Detecting AI-Generated Images via CLIP
par: Moskowitz, A. G., et autres
Publié: (2024)

Model Stock: All we need is just a few fine-tuned models
par: Jang, Dong-Hwan, et autres
Publié: (2024)

An Empirical Study Into What Matters for Calibrating Vision-Language Models
par: Tu, Weijie, et autres
Publié: (2024)