Imagen de Portada

PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Dreyer, Maximilian, Purelku, Erblina, Vielhaben, Johanna, Samek, Wojciech, Lapuschkin, Sebastian
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP
por: Hufe, Lorenz, et al.
Publicado: (2025)

Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression
por: Bareeva, Dilyara, et al.
Publicado: (2024)

Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations
por: Dreyer, Maximilian, et al.
Publicado: (2023)

Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples
por: Bouanani, Oussama, et al.
Publicado: (2026)

AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
por: Achtibat, Reduan, et al.
Publicado: (2024)

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

Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
por: Hatefi, Sayed Mohammad Vakilzadeh, et al.
Publicado: (2024)

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

Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data
por: Pahde, Frederik, et al.
Publicado: (2025)

Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
por: Pahde, Frederik, et al.
Publicado: (2022)

Human-Centered Evaluation of XAI Methods
por: Dawoud, Karam, et al.
Publicado: (2023)

Mechanistic understanding and validation of large AI models with SemanticLens
por: Dreyer, Maximilian, et al.
Publicado: (2025)

Explainable concept mappings of MRI: Revealing the mechanisms underlying deep learning-based brain disease classification
por: Tinauer, Christian, et al.
Publicado: (2024)

Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks
por: Blücher, Stefan, et al.
Publicado: (2024)

FeatInv: Spatially resolved mapping from feature space to input space using conditional diffusion models
por: Neukirch, Nils, et al.
Publicado: (2025)

SCAM: A Real-World Typographic Robustness Evaluation for Multimodal Foundation Models
por: Westerhoff, Justus, et al.
Publicado: (2025)

From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
por: Achtibat, Reduan, et al.
Publicado: (2022)

ECQ$^{\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs
por: Becking, Daniel, et al.
Publicado: (2021)

XAI-guided Insulator Anomaly Detection for Imbalanced Datasets
por: Hoefler, Maximilian Andreas, et al.
Publicado: (2024)

From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance
por: Dreyer, Maximilian, et al.
Publicado: (2025)

Playing the network backward: A Game Theoretic Attribution Framework
por: Zimmermann, Jakob Paul, et al.
Publicado: (2026)

Iterative Inference in a Chess-Playing Neural Network
por: Sandmann, Elias, et al.
Publicado: (2025)

CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification
por: Yu, Wenlong, et al.
Publicado: (2025)

A Fresh Look at Sanity Checks for Saliency Maps
por: Hedström, Anna, et al.
Publicado: (2024)

Deep Learning-based Multi Project InP Wafer Simulation for Unsupervised Surface Defect Detection
por: Cantú, Emílio Dolgener, et al.
Publicado: (2025)

Disentangling Polysemantic Neurons with a Null-Calibrated Polysemanticity Index and Causal Patch Interventions
por: Gupta, Manan, et al.
Publicado: (2025)

Manipulating Feature Visualizations with Gradient Slingshots
por: Bareeva, Dilyara, et al.
Publicado: (2024)

Fractional Diffusion Bridge Models
por: Nobis, Gabriel, et al.
Publicado: (2025)

Relevance-driven Input Dropout: an Explanation-guided Regularization Technique
por: Gururaj, Shreyas, et al.
Publicado: (2025)

Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs
por: Hatefi, Sayed Mohammad Vakilzadeh, et al.
Publicado: (2025)

Explaining Predictive Uncertainty by Exposing Second-Order Effects
por: Bley, Florian, et al.
Publicado: (2024)

From Attribution to Action: A Human-Centered Application of Activation Steering
por: Labarta, Tobias, et al.
Publicado: (2026)

Circuit Insights: Towards Interpretability Beyond Activations
por: Golimblevskaia, Elena, et al.
Publicado: (2025)

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

Learning Robust Convolutional Neural Networks with Relevant Feature Focusing via Explanations
por: Adachi, Kazuki, et al.
Publicado: (2022)

DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations
por: Augustin, Maximilian, et al.
Publicado: (2023)

Synthetic Generation of Dermatoscopic Images with GAN and Closed-Form Factorization
por: Mekala, Rohan Reddy, et al.
Publicado: (2024)

Atlas-Alignment: Making Interpretability Transferable Across Language Models
por: Puri, Bruno, et al.
Publicado: (2025)

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

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