SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
Paper • 2503.11576 • Published • 161
samunder singh
321samthakur
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 16 days ago
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation upvoted a paper about 2 months ago
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D WorldsOrganizations
