NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval Paper • 2603.12824 • Published 5 days ago • 5
NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval Paper • 2603.12824 • Published 5 days ago • 5
Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late Interaction Paper • 2603.09930 • Published 8 days ago
Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late Interaction Paper • 2603.09930 • Published 8 days ago
NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval Paper • 2603.12824 • Published 5 days ago • 5
view article Article NanoVDR: A 70M Text-Only Model That Retrieves Visual Documents as Well as a 2B VLM 2 days ago • 3
view article Article NanoVDR: A 70M Text-Only Model That Retrieves Visual Documents as Well as a 2B VLM 2 days ago • 3