{"total":42,"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":"2311.07470","title":"Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers","created":"2023-11-13","cited_by_count":36,"area":"mllm"},{"id":"2503.14911","title":"Derm1M: A Million-scale Vision-Language Dataset Aligned with Clinical Ontology Knowledge for Dermatology","created":"2025-03-19","cited_by_count":28,"area":"mllm"},{"id":"2402.16832","title":"Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space","created":"2024-02-26","cited_by_count":22,"area":"mllm"},{"id":"2404.12652","title":"Pre-trained Vision-Language Models Learn Discoverable Visual Concepts","created":"2024-04-19","cited_by_count":16,"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":"2408.02001","title":"AdaCBM: An Adaptive Concept Bottleneck Model for Explainable and Accurate Diagnosis","created":"2024-08-04","cited_by_count":12,"area":"mllm"},{"id":"2409.08202","title":"What Makes a Maze Look Like a Maze?","created":"2024-09-12","cited_by_count":11,"area":"mllm"},{"id":"2311.14339","title":"Towards Concept-based Interpretability of Skin Lesion Diagnosis using Vision-Language Models","created":"2023-11-24","cited_by_count":9,"area":"mllm"},{"id":"2410.10308","title":"LG-CAV: Train Any Concept Activation Vector with Language Guidance","created":"2024-10-14","cited_by_count":9,"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":"2502.15809","title":"Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition","created":"2025-02-19","cited_by_count":7,"area":"mllm"},{"id":"2501.12266","title":"CBVLM: Training-free Explainable Concept-based Large Vision Language Models for Medical Image Classification","created":"2025-01-21","cited_by_count":4,"area":"mllm"},{"id":"2503.02917","title":"Interpretable Few-Shot Retinal Disease Diagnosis with Concept-Guided Prompting of Vision-Language Models","created":"2025-03-04","cited_by_count":4,"area":"mllm"},{"id":"2510.03903","title":"Zero-Shot Fine-Grained Image Classification Using Large Vision-Language Models","created":"2025-10-04","cited_by_count":4,"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":"2603.28211","title":"Explaining CLIP Zero-shot Predictions Through Concepts","created":"2026-03-30","cited_by_count":3,"area":"mllm"},{"id":"2305.14882","title":"Dynamic Clue Bottlenecks: Towards Interpretable-by-Design Visual Question Answering","created":"2023-05-24","cited_by_count":2,"area":"mllm"},{"id":"2406.03071","title":"Exploiting LMM-based knowledge for image classification tasks","created":"2024-06-05","cited_by_count":2,"area":"mllm"},{"id":"2412.18675","title":"TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models","created":"2024-12-24","cited_by_count":2,"area":"mllm"},{"id":"2512.00713","title":"Concept-Guided Backdoor Attack on Vision Language Models","created":"2025-11-30","cited_by_count":2,"area":"mllm"},{"id":"2601.20075","title":"Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive Learning","created":"2026-01-27","cited_by_count":2,"area":"mllm"},{"id":"2606.04180","title":"KODA: Contrastive Representation Comparison and Alignment for Vision-Language Foundation Models","created":"2026-06-02","cited_by_count":2,"area":"mllm"},{"id":"2406.14862","title":"LatentExplainer: Explaining Latent Representations in Deep Generative Models with Multimodal Large Language Models","created":"2024-06-21","cited_by_count":1,"area":"mllm"},{"id":"2410.08469","title":"Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP","created":"2024-10-11","cited_by_count":1,"area":"mllm"},{"id":"2503.16724","title":"Towards Automated Semantic Interpretability in Reinforcement Learning via Vision-Language Models","created":"2025-03-20","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":"2511.06678","title":"Flexible Concept Bottleneck Model","created":"2025-11-10","cited_by_count":1,"area":"mllm"},{"id":"2602.19442","title":"UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignment","created":"2026-02-23","cited_by_count":1,"area":"mllm"},{"id":"2603.21484","title":"Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models","created":"2026-03-23","cited_by_count":1,"area":"mllm"},{"id":"2510.23253","title":"A Video Is Not Worth a Thousand Words","created":"2025-10-27","cited_by_count":0,"area":"mllm"},{"id":"2512.21414","title":"A Tool Bottleneck Framework for Clinically-Informed and Interpretable Medical Image Understanding","created":"2025-12-24","cited_by_count":0,"area":"mllm"},{"id":"2602.15650","title":"Concept-Enhanced Multimodal RAG: Towards Interpretable and Accurate Radiology Report Generation","created":"2026-02-17","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":"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":"2605.22679","title":"Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models","created":"2026-05-21","cited_by_count":0,"area":"mllm"},{"id":"2606.30498","title":"On the Faithfulness of Post-Hoc Concept Bottleneck Models","created":"2026-06-29","cited_by_count":0,"area":"mllm"},{"id":"2607.18695","title":"Attributes Should Come from Images, Not Class Names: Distribution-Conditioned Attribute Selection for Vision-Language Models","created":"2026-07-21","cited_by_count":0,"area":"mllm"},{"id":"2609.21879","title":"Benchmarking the Explanatory Quality of Open-Weight Vision-Language Models in Face Recognition","created":"2026-09-18","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}