{"total":15,"rows":[{"id":"2404.03214","title":"LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity","created":"2024-04-04","cited_by_count":33,"area":null},{"id":"2403.14552","title":"Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer","created":"2024-03-21","cited_by_count":19,"area":null},{"id":"2503.14640","title":"Dynamic Accumulated Attention Map for Interpreting Evolution of Decision-Making in Vision Transformer","created":"2025-03-18","cited_by_count":12,"area":null},{"id":"2507.04388","title":"Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers","created":"2025-07-06","cited_by_count":6,"area":null},{"id":"2403.04523","title":"T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers","created":"2024-03-07","cited_by_count":4,"area":null},{"id":"2602.06613","title":"DAVE: Distribution-aware Attribution via ViT Gradient Decomposition","created":"2026-02-06","cited_by_count":4,"area":null},{"id":"2511.13081","title":"Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2410.07711","title":"AdaptGrad: Adaptive Sampling to Reduce Noise","created":"2024-10-10","cited_by_count":2,"area":null},{"id":"2603.08309","title":"Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2412.08513","title":"REPEAT: Improving Uncertainty Estimation in Representation Learning Explainability","created":"2024-12-11","cited_by_count":1,"area":null},{"id":"2407.00371","title":"Axiomatization of Gradient Smoothing in Neural Networks","created":"2024-06-29","cited_by_count":0,"area":null},{"id":"2509.04588","title":"Beyond Output Faithfulness: Learning Attributions that Preserve Computational Pathways","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2606.03885","title":"Attribution via Distributional Paths for Information Revelation","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2609.07213","title":"Unraveling the Real Working Mechanism and Inherent Flaws of GAE: A Method for Interpreting Transformer Processes from an Economic Perspective","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2610.04605","title":"ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}