retrieval performance
- Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning
- Beyond Modality Collapse: Representation Blending for Multimodal Dataset Distillation
- Find your Needle: Small Object Image Retrieval via Multi-Object Attention Optimization
- Mitigating Semantic Collapse in Partially Relevant Video Retrieval
- VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning