{"total":20,"rows":[{"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":"2402.18695","title":"Grounding Language Models for Visual Entity Recognition","created":"2024-02-28","cited_by_count":12,"area":null},{"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":"2505.15877","title":"Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2601.20131","title":"Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms","created":"2026-01-27","cited_by_count":4,"area":null},{"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":"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":"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":"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":"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":"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":"2605.29158","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}],"next_cursor":null}