{"total":51,"rows":[{"id":"2408.04840","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","created":"2024-08-09","cited_by_count":291,"area":"mllm"},{"id":"2412.01720","title":"LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant","created":"2024-12-02","cited_by_count":106,"area":"mllm"},{"id":"2411.02937","title":"Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent","created":"2024-11-05","cited_by_count":65,"area":"mllm"},{"id":"2503.18016","title":"Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook","created":"2025-03-23","cited_by_count":32,"area":"rag"},{"id":"2410.13360","title":"RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models","created":"2024-10-17","cited_by_count":24,"area":"mllm"},{"id":"2506.10408","title":"Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges","created":"2025-06-12","cited_by_count":19,"area":"lr"},{"id":"2510.04401","title":"Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Counting","created":"2025-10-06","cited_by_count":18,"area":"mllm"},{"id":"2510.14605","title":"Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering","created":"2025-10-16","cited_by_count":17,"area":"mllm"},{"id":"2411.00304","title":"Unified Generative and Discriminative Training for Multi-modal Large Language Models","created":"2024-11-01","cited_by_count":15,"area":"mllm"},{"id":"2506.05872","title":"Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection","created":"2025-06-06","cited_by_count":15,"area":null},{"id":"2503.01980","title":"Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval","created":"2025-03-03","cited_by_count":13,"area":"mllm"},{"id":"2402.18695","title":"Grounding Language Models for Visual Entity Recognition","created":"2024-02-28","cited_by_count":12,"area":null},{"id":"2603.00873","title":"MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains","created":"2026-03-01","cited_by_count":12,"area":"lr"},{"id":"2410.03450","title":"MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents","created":"2024-10-04","cited_by_count":11,"area":"agents"},{"id":"2508.05318","title":"mKG-RAG: Leveraging Multimodal Knowledge Graphs in Retrieval-Augmented Generation for Knowledge-intensive VQA","created":"2025-08-07","cited_by_count":11,"area":"mllm"},{"id":"2402.02503","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","created":"2024-02-04","cited_by_count":9,"area":null},{"id":"2408.05337","title":"VACoDe: Visual Augmented Contrastive Decoding","created":"2024-07-26","cited_by_count":8,"area":"mllm"},{"id":"2602.22683","title":"SUPERGLASSES: Benchmarking Vision Language Models as Intelligent Agents for AI Smart Glasses","created":"2026-02-26","cited_by_count":6,"area":"mllm"},{"id":"2505.15877","title":"Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2508.00955","title":"From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model","created":"2025-08-01","cited_by_count":5,"area":"mllm"},{"id":"2601.20131","title":"Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms","created":"2026-01-27","cited_by_count":4,"area":null},{"id":"2401.10712","title":"Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledge","created":"2024-01-19","cited_by_count":3,"area":"lr"},{"id":"2403.10037","title":"Knowledge Condensation and Reasoning for Knowledge-based VQA","created":"2024-03-15","cited_by_count":3,"area":"lr"},{"id":"2506.06962","title":"AR-RAG: Autoregressive Retrieval Augmentation for Image Generation","created":"2025-06-08","cited_by_count":3,"area":null},{"id":"2506.13095","title":"Learning Event Completeness for Weakly Supervised Video Anomaly Detection","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2509.08897","title":"Recurrence Meets Transformers for Universal Multimodal Retrieval","created":"2025-09-10","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":"2603.00550","title":"Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoning","created":"2026-02-28","cited_by_count":3,"area":null},{"id":"2409.01690","title":"Taming CLIP for Fine-grained and Structured Visual Understanding of Museum Exhibits","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2503.18536","title":"DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels","created":"2025-03-24","cited_by_count":2,"area":"diffusion"},{"id":"2511.11132","title":"From Hindsight to Foresight: Self-Encouraged Hindsight Distillation for Knowledge-based Visual Question Answering","created":"2025-11-14","cited_by_count":2,"area":"lr"},{"id":"2511.22843","title":"Breaking the Visual Shortcuts in Multimodal Knowledge-Based Visual Question Answering","created":"2025-11-28","cited_by_count":2,"area":null},{"id":"2601.18195","title":"QualiRAG: Retrieval-Augmented Generation for Visual Quality Understanding","created":"2026-01-26","cited_by_count":2,"area":"rag"},{"id":"2602.06034","title":"V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2602.23952","title":"CC-VQA: Conflict- and Correlation-Aware Method for Mitigating Knowledge Conflict in Knowledge-Based Visual Question Answering","created":"2026-02-27","cited_by_count":2,"area":null},{"id":"2605.06460","title":"MINER: Mining Multimodal Internal Representation for Efficient Retrieval","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2507.22933","title":"Augmented Vision-Language Models: A Systematic Review","created":"2025-07-24","cited_by_count":1,"area":"mllm"},{"id":"2509.02123","title":"CMRAG: Co-modality-based visual document retrieval and question answering","created":"2025-09-02","cited_by_count":1,"area":"rag"},{"id":"2601.21853","title":"LEMUR: Learned Multi-Vector Retrieval","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2605.16834","title":"Learning Relative Representations for Fine-Grained Multimodal Alignment with Limited Data","created":"2026-05-16","cited_by_count":1,"area":null},{"id":"2509.09159","title":"A Knowledge Noise Mitigation Framework for Knowledge-based Visual Question Answering","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2602.06050","title":"Relevance-aware Multi-context Contrastive Decoding for Retrieval-augmented Visual Question Answering","created":"2026-01-14","cited_by_count":0,"area":"mllm"},{"id":"2603.13537","title":"AMES: Approximate Multi-modal Enterprise Search via Late Interaction Retrieval","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2604.25296","title":"Learning from Medical Entity Trees: An Entity-Centric Medical Data Engineering Framework for MLLMs","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2605.07273","title":"From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAG","created":"2026-05-08","cited_by_count":0,"area":"rag"},{"id":"2605.10120","title":"MicroWorld: Empowering Multimodal Large Language Models to Bridge the Microscopic Domain Gap with Multimodal Attribute Graph","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.29158","title":"PROTOCOL: Late Interaction Retrieval for Protein Homolog Search","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.16208","title":"ColGraphRAG: Late-Interaction Evidence Retrieval for Multimodal GraphRAG","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2607.25422","title":"Salient Knowledge Pathways: Sparse Cross-Modal Routing for Efficient Knowledge-Intensive Multimodal Question Answering","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.22688","title":"FashionKG-RAG: Knowledge Graph-Enhanced Retrieval-Augmented Generation for Fashion Question Answering","created":"2026-08-24","cited_by_count":0,"area":"rag"},{"id":"2609.16847","title":"RegRet: Enhancing Region-Level Retrieval in Large Multimodal Models","created":"2026-09-15","cited_by_count":0,"area":"mllm"}],"next_cursor":null}