{"total":47,"rows":[{"id":"2308.03685","title":"Learning Concise and Descriptive Attributes for Visual Recognition","created":"2023-08-07","cited_by_count":73,"area":"mllm"},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2411.16721","title":"Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks","created":"2024-11-23","cited_by_count":48,"area":"mllm"},{"id":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2506.23270","title":"Token Activation Map to Visually Explain Multimodal LLMs","created":"2025-06-29","cited_by_count":32,"area":"mllm"},{"id":"2406.16320","title":"What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation","created":"2024-06-24","cited_by_count":30,"area":"mllm"},{"id":"2404.06332","title":"X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Model","created":"2024-04-07","cited_by_count":22,"area":"mllm"},{"id":"2407.14412","title":"DEAL: Disentangle and Localize Concept-level Explanations for VLMs","created":"2024-07-19","cited_by_count":14,"area":"mllm"},{"id":"2408.09916","title":"Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit","created":"2024-08-19","cited_by_count":14,"area":"mllm"},{"id":"2502.11073","title":"Demystifying Hateful Content: Leveraging Large Multimodal Models for Hateful Meme Detection with Explainable Decisions","created":"2025-02-16","cited_by_count":14,"area":"mllm"},{"id":"2402.12198","title":"Exploring the Limits of Zero Shot Vision Language Models for Hate Meme Detection: The Vulnerabilities and their Interpretations","created":"2024-02-19","cited_by_count":10,"area":"mllm"},{"id":"2503.06670","title":"Attention, Please! PixelSHAP Reveals What Vision-Language Models Actually Focus On","created":"2025-03-09","cited_by_count":9,"area":"mllm"},{"id":"2502.18816","title":"Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP","created":"2025-02-26","cited_by_count":8,"area":"mllm"},{"id":"2312.17345","title":"3VL: Using Trees to Improve Vision-Language Models' Interpretability","created":"2023-12-28","cited_by_count":7,"area":"mllm"},{"id":"2503.22720","title":"Why Representation Engineering Works: A Theoretical and Empirical Study in Vision-Language Models","created":"2025-03-25","cited_by_count":6,"area":"mllm"},{"id":"2502.00262","title":"INSIGHT: Enhancing Autonomous Driving Safety through Vision-Language Models on Context-Aware Hazard Detection and Edge Case Evaluation","created":"2025-02-01","cited_by_count":5,"area":"mllm"},{"id":"2509.22415","title":"Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models","created":"2025-09-26","cited_by_count":5,"area":"mllm"},{"id":"2404.12839","title":"ECOR: Explainable CLIP for Object Recognition","created":"2024-04-19","cited_by_count":4,"area":"mllm"},{"id":"2408.12808","title":"VALE: A Multimodal Visual and Language Explanation Framework for Image Classifiers using eXplainable AI and Language Models","created":"2024-08-23","cited_by_count":4,"area":"mllm"},{"id":"2503.10857","title":"Towards Understanding Graphical Perception in Large Multimodal Models","created":"2025-03-13","cited_by_count":4,"area":"mllm"},{"id":"2403.02558","title":"The Minimum Information about CLinical Artificial Intelligence Checklist for Generative Modeling Research (MI-CLAIM-GEN)","created":"2024-03-05","cited_by_count":3,"area":"mllm"},{"id":"2511.12978","title":"Concept Regions Matter: Benchmarking CLIP with a New Cluster-Importance Approach","created":"2025-11-17","cited_by_count":3,"area":"mllm"},{"id":"2602.20577","title":"Efficient and Explainable End-to-End Autonomous Driving via Masked Vision-Language-Action Diffusion","created":"2026-02-24","cited_by_count":2,"area":"mllm"},{"id":"2609.00868","title":"The Visual Insensitivity Gap: Diagnosing When Vision-Language Models Fail to Use Visual Evidence","created":"2026-09-01","cited_by_count":2,"area":"mllm"},{"id":"2503.11360","title":"PARIC: Probabilistic Attention Regularization for Language Guided Image Classification from Pre-trained Vison Language Models","created":"2025-03-14","cited_by_count":1,"area":"mllm"},{"id":"2508.14280","title":"Multi-Rationale Explainable Object Recognition via Contrastive Conditional Inference","created":"2025-08-19","cited_by_count":1,"area":"mllm"},{"id":"2508.16661","title":"QA-VLM: Providing human-interpretable quality assessment for wire-feed laser additive manufacturing parts with Vision Language Models","created":"2025-08-20","cited_by_count":1,"area":"mllm"},{"id":"2604.11005","title":"Diffusion-CAM: Faithful Visual Explanations for dMLLMs","created":"2026-04-13","cited_by_count":1,"area":"mllm"},{"id":"2604.17126","title":"Prompt Sensitivity in Vision-Language Grounding: How Small Changes in Wording Affect Object Detection","created":"2026-04-18","cited_by_count":1,"area":"mllm"},{"id":"2605.06058","title":"Towards Self-Explainable Document Visual Question Answering with Chain-of-Explanation Predictions","created":"2026-05-07","cited_by_count":1,"area":"mllm"},{"id":"2606.18008","title":"PhaseWin: An Efficient Search Algorithm for Faithful Visual Attribution","created":"2026-06-16","cited_by_count":1,"area":"mllm"},{"id":"2506.18201","title":"Deciphering Emotions in Children Storybooks: A Comparative Analysis of Multimodal LLMs in Educational Applications","created":"2025-06-22","cited_by_count":0,"area":"mllm"},{"id":"2603.08921","title":"Vision-Language Models Encode Clinical Guidelines for Concept-Based Medical Reasoning","created":"2026-03-09","cited_by_count":0,"area":"mllm"},{"id":"2603.25403","title":"Shape and Substance: Dual-Layer Side-Channel Attacks on Local Vision-Language Models","created":"2026-03-26","cited_by_count":0,"area":"mllm"},{"id":"2603.26798","title":"Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings","created":"2026-03-26","cited_by_count":0,"area":"mllm"},{"id":"2604.07692","title":"Tree-of-Evidence: Efficient \"System 2\" Search for Faithful Multimodal Grounding","created":"2026-04-09","cited_by_count":0,"area":"mllm"},{"id":"2604.15748","title":"Concept-wise Attention for Fine-grained Concept Bottleneck Models","created":"2026-04-17","cited_by_count":0,"area":"mllm"},{"id":"2605.05593","title":"Causal Probing for Internal Visual Representations in Multimodal Large Language Models","created":"2026-05-07","cited_by_count":0,"area":"mllm"},{"id":"2605.13047","title":"Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency","created":"2026-05-13","cited_by_count":0,"area":"mllm"},{"id":"2606.07531","title":"mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models","created":"2026-04-21","cited_by_count":0,"area":"mllm"},{"id":"2606.16137","title":"XAI-Grounded Explanation Generation for Speech Deepfake Detection with Training-Free Multimodal Large Language Models","created":"2026-06-15","cited_by_count":0,"area":"mllm"},{"id":"2607.16105","title":"Attention-Guided Saliency Maps for Interpreting Visualization Literacy in VLMs","created":"2026-07-17","cited_by_count":0,"area":"mllm"},{"id":"2608.24430","title":"Vision Language Model Fusion for Explainable Face Recognition","created":"2026-08-25","cited_by_count":0,"area":"mllm"},{"id":"2608.24910","title":"From Plots to Words: Model-Aware Multimodal Explanations as a Foundation for Accessible, Non-Visual Interaction","created":"2026-07-22","cited_by_count":0,"area":"mllm"},{"id":"2608.24934","title":"Fusing Perceptual Vision Experts with Multimodal Large Language Models for Explainable Plant Disease Diagnosis: From Benchmark Imagery to Real-World Robotic Field Validation","created":"2026-08-23","cited_by_count":0,"area":"mllm"},{"id":"2609.24470","title":"Spatial Action Review: A Visual Analytics Dashboard for Auditing Language-to-Action Hand-offs in Electron Microscopy","created":"2026-09-21","cited_by_count":0,"area":"mllm"},{"id":"2609.37786","title":"CHOQOLATE: Organizing Concept Bottleneck Latent Spaces with Choquet Integrals","created":"2026-09-29","cited_by_count":0,"area":"mllm"}],"next_cursor":null}