Cover Image

Your CLIP has 164 dimensions of noise: Exploring the embeddings covariance eigenspectrum of contrastively pretrained vision-language transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Grzywaczewski, Jakub, Płudowski, Dawid, Biecek, Przemysław
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

SwordBench: Evaluating Orthogonality of Steering Image Representations
by: Zaigrajew, Vladimir, et al.
Published: (2026)

Rethinking Visual Counterfactual Explanations Through Region Constraint
by: Sobieski, Bartlomiej, et al.
Published: (2024)

Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models
by: Sobieski, Bartlomiej, et al.
Published: (2026)

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

Auditing Sybil: Explaining Deep Lung Cancer Risk Prediction Through Generative Interventional Attributions
by: Sobieski, Bartlomiej, et al.
Published: (2026)

Position: Do Not Explain Vision Models Without Context
by: Tomaszewska, Paulina, et al.
Published: (2024)

Global Counterfactual Directions
by: Sobieski, Bartlomiej, et al.
Published: (2024)

Adversarial attacks and defenses in explainable artificial intelligence: A survey
by: Baniecki, Hubert, et al.
Published: (2023)

CNN-based explanation ensembling for dataset, representation and explanations evaluation
by: Hryniewska-Guzik, Weronika, et al.
Published: (2024)

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

NormEnsembleXAI: Unveiling the Strengths and Weaknesses of XAI Ensemble Techniques
by: Hryniewska-Guzik, Weronika, et al.
Published: (2024)

X-ray transferable polyrepresentation learning
by: Hryniewska-Guzik, Weronika, et al.
Published: (2025)

Red Teaming Models for Hyperspectral Image Analysis Using Explainable AI
by: Zaigrajew, Vladimir, et al.
Published: (2024)

Birds look like cars: Adversarial analysis of intrinsically interpretable deep learning
by: Baniecki, Hubert, et al.
Published: (2025)

Self-supervised pretraining for an iterative image size agnostic vision transformer
by: Prisadnikov, Nedyalko, et al.
Published: (2026)

Red-Teaming Segment Anything Model
by: Jankowski, Krzysztof, et al.
Published: (2024)

AEGIS: Preserving privacy of 3D Facial Avatars with Adversarial Perturbations
by: Wolkiewicz, Dawid, et al.
Published: (2025)

Does context matter in digital pathology?
by: Tomaszewska, Paulina, et al.
Published: (2024)

Harnessing small projectors and multiple views for efficient vision pretraining
by: Agrawal, Kumar Krishna, et al.
Published: (2023)

LINE: LLM-based Iterative Neuron Explanations for Vision Models
by: Zaigrajew, Vladimir, et al.
Published: (2026)

The effectiveness of MAE pre-pretraining for billion-scale pretraining
by: Singh, Mannat, et al.
Published: (2023)

CLIPin: A Non-contrastive Plug-in to CLIP for Multimodal Semantic Alignment
by: Yang, Shengzhu, et al.
Published: (2025)

The Dark Patterns of Personalized Persuasion in Large Language Models: Exposing Persuasive Linguistic Features for Big Five Personality Traits in LLMs Responses
by: Mieleszczenko-Kowszewicz, Wiktoria, et al.
Published: (2024)

Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions
by: Baniecki, Hubert, et al.
Published: (2025)

Interpretable machine learning for time-to-event prediction in medicine and healthcare
by: Baniecki, Hubert, et al.
Published: (2023)

SmartCLIP: Modular Vision-language Alignment with Identification Guarantees
by: Xie, Shaoan, et al.
Published: (2025)

Swin SMT: Global Sequential Modeling in 3D Medical Image Segmentation
by: Płotka, Szymon, et al.
Published: (2024)

A comparative analysis of deep learning models for lung segmentation on X-ray images
by: Hryniewska-Guzik, Weronika, et al.
Published: (2024)

Deep spatial context: when attention-based models meet spatial regression
by: Tomaszewska, Paulina, et al.
Published: (2024)

Context-self contrastive pretraining for crop type semantic segmentation
by: Tarasiou, Michail, et al.
Published: (2021)

UnGuide: Learning to Forget with LoRA-Guided Diffusion Models
by: Polowczyk, Agnieszka, et al.
Published: (2025)

Are vision language models robust to uncertain inputs?
by: Wang, Xi, et al.
Published: (2025)

Neural Surface Priors for Editable Gaussian Splatting
by: Szymkowiak, Jakub, et al.
Published: (2024)

EyeCLIP: A visual-language foundation model for multi-modal ophthalmic image analysis
by: Shi, Danli, et al.
Published: (2024)

Aggregated Attributions for Explanatory Analysis of 3D Segmentation Models
by: Chrabaszcz, Maciej, et al.
Published: (2024)

Quantifying the human visual exposome with vision language models
by: Rominger, Christian, et al.
Published: (2026)

What matters when building vision-language models?
by: Laurençon, Hugo, et al.
Published: (2024)

Interpreting vision transformers via residual replacement model
by: Kim, Jinyeong, et al.
Published: (2025)

Intuitive physics understanding emerges from self-supervised pretraining on natural videos
by: Garrido, Quentin, et al.
Published: (2025)

Reproducible scaling laws for contrastive language-image learning
by: Cherti, Mehdi, et al.
Published: (2022)