NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval
Paper • 2603.12824 • Published • 5
Zhuchenyang Liu
Ryenhails
AI & ML interests
None yet
Recent Activity
updated a Space 5 days ago
nanovdr/README updated a model 5 days ago
nanovdr/NanoVDR-L-Multi published a model 5 days ago
nanovdr/NanoVDR-L-MultiOrganizations
upvoted a paper 6 days ago
upvoted an article 7 days ago
Article
NanoVDR: A 70M Text-Only Model That Retrieves Visual Documents as Well as a 2B VLM
•
3
upvoted 2
articles 2 months ago
Article
LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family
•
88
Article
How We Built a Semantic Highlight Model To Save Token Cost for RAG
•
65