{"total":24,"rows":[{"id":"2503.02199","title":"Words or Vision: Do Vision-Language Models Have Blind Faith in Text?","created":"2025-03-04","cited_by_count":89,"area":"mllm"},{"id":"2503.01222","title":"Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG","created":"2025-03-03","cited_by_count":23,"area":"mllm"},{"id":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2412.06141","title":"MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization","created":"2024-12-09","cited_by_count":21,"area":"mllm"},{"id":"2505.23601","title":"EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis","created":"2025-05-29","cited_by_count":14,"area":"mllm"},{"id":"2512.16201","title":"Visual Alignment of Medical Vision-Language Models for Grounded Radiology Report Generation","created":"2025-12-18","cited_by_count":5,"area":"mllm"},{"id":"2505.20444","title":"HoPE: Hybrid of Position Embedding for Long Context Vision-Language Models","created":"2025-05-26","cited_by_count":4,"area":"mllm"},{"id":"2507.07902","title":"MIRA: A Novel Framework for Fusing Modalities in Medical RAG","created":"2025-07-10","cited_by_count":4,"area":"mllm"},{"id":"2507.09209","title":"Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models","created":"2025-07-12","cited_by_count":4,"area":"mllm"},{"id":"2509.23379","title":"CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding","created":"2025-09-27","cited_by_count":4,"area":"mllm"},{"id":"2508.18805","title":"Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models","created":"2025-08-26","cited_by_count":3,"area":"mllm"},{"id":"2511.15435","title":"HV-Attack: Hierarchical Visual Attack for Multimodal Retrieval Augmented Generation","created":"2025-11-19","cited_by_count":3,"area":"mllm"},{"id":"2506.07399","title":"MrM: Black-Box Membership Inference Attacks against Multimodal RAG Systems","created":"2025-06-09","cited_by_count":2,"area":"mllm"},{"id":"2508.10955","title":"Empowering Multimodal LLMs with External Tools: A Comprehensive Survey","created":"2025-08-14","cited_by_count":2,"area":"mllm"},{"id":"2508.06496","title":"Med-GRIM: Enhanced Zero-Shot Medical VQA using prompt-embedded Multimodal Graph RAG","created":"2025-07-20","cited_by_count":1,"area":"mllm"},{"id":"2508.12778","title":"HeteroRAG: A Heterogeneous Retrieval-Augmented Generation Framework for Medical Vision Language Tasks","created":"2025-08-18","cited_by_count":1,"area":"mllm"},{"id":"2512.05959","title":"M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG","created":"2025-12-05","cited_by_count":1,"area":"mllm"},{"id":"2601.11632","title":"KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering","created":"2026-01-14","cited_by_count":1,"area":"mllm"},{"id":"2610.09146","title":"Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI","created":"2026-10-06","cited_by_count":1,"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":"2603.00172","title":"Hidden in the Metadata: Stealth Poisoning Attacks on Multimodal Retrieval-Augmented Generation","created":"2026-02-26","cited_by_count":0,"area":"mllm"},{"id":"2605.06173","title":"Retina-RAG: Retrieval-Augmented Vision-Language Modeling for Joint Retinal Diagnosis and Clinical Report Generation","created":"2026-05-07","cited_by_count":0,"area":"mllm"},{"id":"2609.22162","title":"Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation","created":"2026-08-26","cited_by_count":0,"area":"mllm"},{"id":"2610.01871","title":"Walking the Embedding Space: Datastore Extraction from Multimodal RAG","created":"2026-10-01","cited_by_count":0,"area":"mllm"}],"next_cursor":null}