{"total":28,"rows":[{"id":"2504.02821","title":"Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models","created":"2025-04-03","cited_by_count":71,"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":"2406.08074","title":"A Concept-Based Explainability Framework for Large Multimodal Models","created":"2024-06-12","cited_by_count":39,"area":"mllm"},{"id":"2504.11695","title":"Interpreting the linear structure of vision-language model embedding spaces","created":"2025-04-16","cited_by_count":32,"area":"mllm"},{"id":"2602.06218","title":"Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings","created":"2026-02-05","cited_by_count":10,"area":"mllm"},{"id":"2508.05430","title":"Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions","created":"2025-08-07","cited_by_count":6,"area":"mllm"},{"id":"2506.17265","title":"SUA: Stealthy Multimodal Large Language Model Unlearning Attack","created":"2025-06-10","cited_by_count":4,"area":"mllm"},{"id":"2511.12331","title":"SpaceVLM: Sub-Space Modeling of Negation in Vision-Language Models","created":"2025-11-15","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":"2603.28211","title":"Explaining CLIP Zero-shot Predictions Through Concepts","created":"2026-03-30","cited_by_count":3,"area":"mllm"},{"id":"2602.20853","title":"On the Explainability of Vision-Language Models in Art History","created":"2026-02-24","cited_by_count":2,"area":"mllm"},{"id":"2606.24716","title":"Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations","created":"2026-06-23","cited_by_count":2,"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":"2605.07148","title":"Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models","created":"2026-05-08","cited_by_count":1,"area":"mllm"},{"id":"2606.18839","title":"Semantic Robustness Certification for Vision-Language Models","created":"2026-06-17","cited_by_count":1,"area":"mllm"},{"id":"2507.03542","title":"Beyond Accuracy: Metrics that Uncover What Makes a 'Good' Visual Descriptor","created":"2025-07-04","cited_by_count":0,"area":"mllm"},{"id":"2511.00110","title":"Chain of Time: In-Context Physical Simulation with Image Generation Models","created":"2025-10-30","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":"2603.26798","title":"Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings","created":"2026-03-26","cited_by_count":0,"area":"mllm"},{"id":"2604.05971","title":"Is CLIP Cross-Eyed? Revealing and Mitigating Center Bias in the CLIP Family","created":"2026-04-07","cited_by_count":0,"area":"mllm"},{"id":"2604.11868","title":"MedConcept: Unsupervised Concept Discovery for Interpretability in Medical VLMs","created":"2026-04-13","cited_by_count":0,"area":"mllm"},{"id":"2605.11107","title":"Birds of a Feather Flock Together: Background-Invariant Representations via Linear Structure in VLMs","created":"2026-05-11","cited_by_count":0,"area":"mllm"},{"id":"2605.14309","title":"ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition","created":"2026-05-14","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":"2608.21415","title":"Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding","created":"2026-08-12","cited_by_count":0,"area":"mllm"},{"id":"2609.37638","title":"Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model","created":"2026-09-29","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"},{"id":"2610.00848","title":"Geometric Similarity in VLM Low-Level Vision Representations","created":"2026-10-01","cited_by_count":0,"area":"mllm"}],"next_cursor":null}