Similar Items: One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders via Hubness
- Robust Multimodal Recommendation via Graph Retrieval-Enhanced Modality Completion
- Topic Is Not Agenda: A Citation-Community Audit of Text Embeddings
- Text-Graph Synergy: A Bidirectional Verification and Completion Framework for RAG
- A CLIP-Based Cross-Modal Matching Model for Image-Text Retrieval
- Urban-ImageNet: A Large-Scale Multi-Modal Dataset and Evaluation Framework for Urban Space Perception
- Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding