{"total":52,"rows":[{"id":"2401.15947","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","created":"2024-01-29","cited_by_count":300,"area":"mllm"},{"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":"2311.16494","title":"ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models","created":"2023-11-27","cited_by_count":39,"area":"mllm"},{"id":"2405.12255","title":"Mammo-CLIP: A Vision Language Foundation Model to Enhance Data Efficiency and Robustness in Mammography","created":"2024-05-20","cited_by_count":38,"area":"mllm"},{"id":"2403.12952","title":"Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models","created":"2024-03-19","cited_by_count":32,"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":"2403.07636","title":"Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework","created":"2024-03-12","cited_by_count":27,"area":"mllm"},{"id":"2507.19024","title":"A Survey of Multimodal Hallucination Evaluation and Detection","created":"2025-07-25","cited_by_count":27,"area":"mllm"},{"id":"2407.11335","title":"LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction","created":"2024-07-16","cited_by_count":19,"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":"2410.15364","title":"Scene Graph Generation with Role-Playing Large Language Models","created":"2024-10-20","cited_by_count":16,"area":"mllm"},{"id":"2403.16442","title":"If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions","created":"2024-03-25","cited_by_count":14,"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":"2311.07593","title":"Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification","created":"2023-11-10","cited_by_count":13,"area":"mllm"},{"id":"2409.19961","title":"Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval","created":"2024-09-30","cited_by_count":13,"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":"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":"2307.11315","title":"GIST: Generating Image-Specific Text for Fine-grained Object Classification","created":"2023-07-21","cited_by_count":8,"area":"mllm"},{"id":"2501.13982","title":"Attribute-based Visual Reprogramming for Vision-Language Models","created":"2025-01-23","cited_by_count":8,"area":"mllm"},{"id":"2402.14891","title":"LLMBind: A Unified Modality-Task Integration Framework","created":"2024-02-22","cited_by_count":7,"area":"mllm"},{"id":"2410.11201","title":"Tree of Attributes Prompt Learning for Vision-Language Models","created":"2024-10-15","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":"2407.09073","title":"Open Vocabulary Multi-Label Video Classification","created":"2024-07-12","cited_by_count":5,"area":"mllm"},{"id":"2511.12639","title":"Medical Knowledge Intervention Prompt Tuning for Medical Image Classification","created":"2025-11-16","cited_by_count":5,"area":"mllm"},{"id":"2410.23698","title":"Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP","created":"2024-10-31","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":"2504.20860","title":"FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models","created":"2025-04-29","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":"2307.07341","title":"PiTL: Cross-modal Retrieval with Weakly-supervised Vision-language Pre-training via Prompting","created":"2023-07-14","cited_by_count":3,"area":"mllm"},{"id":"2412.13947","title":"Real Classification by Description: Extending CLIP's Limits of Part Attributes Recognition","created":"2024-12-18","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":"2404.16717","title":"Embracing Diversity: Interpretable Zero-shot classification beyond one vector per class","created":"2024-04-25","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":"2507.08410","title":"Multi-modal Mutual-Guidance Conditional Prompt Learning for Vision-Language Models","created":"2025-07-11","cited_by_count":2,"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":"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":"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":"2307.06795","title":"Leveraging Vision-Language Foundation Models for Fine-Grained Downstream Tasks","created":"2023-07-13","cited_by_count":0,"area":"mllm"},{"id":"2405.07921","title":"Can Better Text Semantics in Prompt Tuning Improve VLM Generalization?","created":"2024-05-13","cited_by_count":0,"area":"mllm"},{"id":"2412.11663","title":"LMM-Regularized CLIP Embeddings for Image Classification","created":"2024-12-16","cited_by_count":0,"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":"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":"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":"2604.15748","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":"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":"2608.28696","title":"Instruction Distillation: Text Instructions as Visual Examples","created":"2026-08-27","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":"2610.16666","title":"Revisiting Natural Language Prompts from Large Language Models for Open-Vocabulary Video Recognition","created":"2026-10-12","cited_by_count":0,"area":"mllm"}],"next_cursor":null}