Cover Image

Quantifying Structure in CLIP Embeddings: A Statistical Framework for Concept Interpretation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhao, Jitian, Li, Chenghui, Sala, Frederic, Rohe, Karl
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

OTTER: Effortless Label Distribution Adaptation of Zero-shot Models
by: Shin, Changho, et al.
Published: (2024)

CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation
by: Zhao, Jitian, et al.
Published: (2026)

MoRe Fine-Tuning with 10x Fewer Parameters
by: Tan, Wenxuan, et al.
Published: (2024)

Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models
by: Debot, David, et al.
Published: (2025)

CLIP-Embed-KD: Computationally Efficient Knowledge Distillation Using Embeddings as Teachers
by: Nair, Lakshmi
Published: (2024)

COSMOS: Predictable and Cost-Effective Adaptation of LLMs
by: Wang, Jiayu, et al.
Published: (2025)

Weak-to-Strong Generalization Through the Data-Centric Lens
by: Shin, Changho, et al.
Published: (2024)

Interpretable Spatio-Temporal Embedding for Brain Structural-Effective Network with Ordinary Differential Equation
by: Tang, Haoteng, et al.
Published: (2024)

Time To Impeach LLM-as-a-Judge: Programs are the Future of Evaluation
by: Huang, Tzu-Heng, et al.
Published: (2025)

Leakage and Interpretability in Concept-Based Models
by: Parisini, Enrico, et al.
Published: (2025)

Hierarchical Concept-based Interpretable Models
by: Hill, Oscar, et al.
Published: (2026)

Interpretable Concept-Based Memory Reasoning
by: Debot, David, et al.
Published: (2024)

Interpretable Neural-Symbolic Concept Reasoning
by: Barbiero, Pietro, et al.
Published: (2023)

A General Framework for Producing Interpretable Semantic Text Embeddings
by: Sun, Yiqun, et al.
Published: (2024)

Zero-Shot Robustification of Zero-Shot Models
by: Adila, Dyah, et al.
Published: (2023)

Learning Unbiased Cluster Descriptors for Interpretable Imbalanced Concept Drift Detection
by: Zhang, Yiqun, et al.
Published: (2026)

The Normalized Cross Density Functional: A Framework to Quantify Statistical Dependence for Random Processes
by: Hu, Bo, et al.
Published: (2022)

DRExplainer: Quantifiable Interpretability in Drug Response Prediction with Directed Graph Convolutional Network
by: Shi, Haoyuan, et al.
Published: (2024)

Discovering Chunks in Neural Embeddings for Interpretability
by: Wu, Shuchen, et al.
Published: (2025)

The SaTML '24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability
by: Casper, Stephen, et al.
Published: (2024)

Promises and Pitfalls of Threshold-based Auto-labeling
by: Vishwakarma, Harit, et al.
Published: (2022)

ConceptCaps: a Distilled Concept Dataset for Interpretability in Music Models
by: Sienkiewicz, Bruno, et al.
Published: (2026)

FAA-CLIP: Federated Adversarial Adaptation of CLIP
by: Wu, Yihang, et al.
Published: (2025)

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

Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit
by: Jiang, Nick, et al.
Published: (2025)

Towards Better Generalization and Interpretability in Unsupervised Concept-Based Models
by: De Santis, Francesco, et al.
Published: (2025)

LICORICE: Label-Efficient Concept-Based Interpretable Reinforcement Learning
by: Ye, Zhuorui, et al.
Published: (2024)

Learning to Receive Help: Intervention-Aware Concept Embedding Models
by: Zarlenga, Mateo Espinosa, et al.
Published: (2023)

A Framework for Quantifying How Pre-Training and Context Benefit In-Context Learning
by: Song, Bingqing, et al.
Published: (2025)

Quantifying and Understanding Uncertainty in Large Reasoning Models
by: Li, Yangyi, et al.
Published: (2026)

REMA: A Unified Reasoning Manifold Framework for Interpreting Large Language Model
by: Li, Bo, et al.
Published: (2025)

Concept Tokens: Learning Behavioral Embeddings Through Concept Definitions
by: Sastre, Ignacio, et al.
Published: (2026)

Interpretable Hierarchical Concept Reasoning through Attention-Guided Graph Learning
by: Debot, David, et al.
Published: (2025)

SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders
by: Cywiński, Bartosz, et al.
Published: (2025)

GlassMol: Interpretable Molecular Property Prediction with Concept Bottleneck Models
by: Rivera, Oscar, et al.
Published: (2026)

E-TCAV: Formalizing Penultimate Proxies for Efficient Concept Based Interpretability
by: Aslam, Hasib, et al.
Published: (2026)

TDHook: A Lightweight Framework for Interpretability
by: Poupart, Yoann
Published: (2025)

Evaluating Sample Utility for Efficient Data Selection by Mimicking Model Weights
by: Huang, Tzu-Heng, et al.
Published: (2025)

TRESTLE: A Model of Concept Formation in Structured Domains
by: MacLellan, Christopher J., et al.
Published: (2024)

Memory-Statistics Tradeoff in Continual Learning with Structural Regularization
by: Li, Haoran, et al.
Published: (2025)