Imagen de Portada

Concept-Based Mechanistic Interpretability Using Structured Knowledge Graphs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chorna, Sofiia, Tarelkina, Kateryna, Berthier, Eloïse, Franchi, Gianni
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A Geometric Unification of Concept Learning with Concept Cones
por: Rocchi--Henry, Alexandre, et al.
Publicado: (2025)

CLIP-QDA: An Explainable Concept Bottleneck Model
por: Kazmierczak, Rémi, et al.
Publicado: (2023)

Enhancing Concept Localization in CLIP-based Concept Bottleneck Models
por: Kazmierczak, Rémi, et al.
Publicado: (2025)

NECO: NEural Collapse Based Out-of-distribution detection
por: Ammar, Mouïn Ben, et al.
Publicado: (2023)

Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
por: Xia, Guoxuan, et al.
Publicado: (2024)

COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP
por: Humblot-Renaux, Galadrielle, et al.
Publicado: (2025)

Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation
por: Franchi, Gianni, et al.
Publicado: (2024)

Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations
por: Xu, Xinyue, et al.
Publicado: (2024)

Explainability for Vision Foundation Models: A Survey
por: Kazmierczak, Rémi, et al.
Publicado: (2025)

Restyling Unsupervised Concept Based Interpretable Networks with Generative Models
por: Parekh, Jayneel, et al.
Publicado: (2024)

Unsupervised Interpretable Basis Extraction for Concept-Based Visual Explanations
por: Doumanoglou, Alexandros, et al.
Publicado: (2023)

Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video
por: Joseph, Sonia, et al.
Publicado: (2025)

ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
por: Lin, Shen, et al.
Publicado: (2026)

Concept-Guided Interpretability via Neural Chunking
por: Wu, Shuchen, et al.
Publicado: (2025)

Walking the Web of Concept-Class Relationships in Incrementally Trained Interpretable Models
por: Agrawal, Susmit, et al.
Publicado: (2025)

Building Optimal Neural Architectures using Interpretable Knowledge
por: Mills, Keith G., et al.
Publicado: (2024)

Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers
por: Jun, Youngjun, et al.
Publicado: (2026)

Prototype-Based Knowledge Guidance for Fine-Grained Structured Radiology Reporting
por: Pellegrini, Chantal, et al.
Publicado: (2026)

Concept-Based Unsupervised Domain Adaptation
por: Xu, Xinyue, et al.
Publicado: (2025)

Bayesian Modeling of Zero-Shot Classifications for Urban Flood Detection
por: Franchi, Matt, et al.
Publicado: (2025)

Measuring the (Un)Faithfulness of Concept-Based Explanations
por: Kumar, Shubham, et al.
Publicado: (2025)

Abstract Art Interpretation Using ControlNet
por: Srivastava, Rishabh, et al.
Publicado: (2024)

Explaining Generalization Power of a DNN Using Interactive Concepts
por: Zhou, Huilin, et al.
Publicado: (2023)

Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits
por: Kalibhat, Neha, et al.
Publicado: (2026)

Detection-Fusion for Knowledge Graph Extraction from Videos
por: Das, Taniya, et al.
Publicado: (2024)

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers
por: Vielhaben, Johanna, et al.
Publicado: (2024)

Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense Knowledge
por: Jiang, Bowen, et al.
Publicado: (2023)

Learning Concept-Based Causal Transition and Symbolic Reasoning for Visual Planning
por: Qian, Yilue, et al.
Publicado: (2023)

Concept Arithmetics for Circumventing Concept Inhibition in Diffusion Models
por: Petsiuk, Vitali, et al.
Publicado: (2024)

Towards a Mechanistic Explanation of Diffusion Model Generalization
por: Niedoba, Matthew, et al.
Publicado: (2024)

Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes
por: Donnelly, Jon, et al.
Publicado: (2021)

A Concept-based Interpretable Model for the Diagnosis of Choroid Neoplasias using Multimodal Data
por: Wu, Yifan, et al.
Publicado: (2024)

Post-Hoc Concept Disentanglement: From Correlated to Isolated Concept Representations
por: Erogullari, Eren, et al.
Publicado: (2025)

Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models
por: Singhi, Nishad, et al.
Publicado: (2024)

Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models
por: Kwon, Gihyun, et al.
Publicado: (2024)

Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning
por: Cao, Xusheng, et al.
Publicado: (2025)

ULTra: Unveiling Latent Token Interpretability in Transformer-Based Understanding and Segmentation
por: Hosseini, Hesam, et al.
Publicado: (2024)

A Robust Prototype-Based Network with Interpretable RBF Classifier Foundations
por: Saralajew, Sascha, et al.
Publicado: (2024)

Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery
por: Rao, Sukrut, et al.
Publicado: (2024)

ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning
por: Chavhan, Ruchika, et al.
Publicado: (2024)