SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
Paper • 2503.11576 • Published • 164
Emmanouil Karystinaios PRO
manoskary
AI & ML interests
Audio-Based Diffusion, Graph Neural Networks and Music Information Retrieval.
Recent Activity
updated a Space 3 days ago
Music-FX/neural-morphing updated a Space 10 days ago
manoskary/piano-engravingOrganizations
upvoted 4
papers 17 days ago
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
Paper • 2606.03264 • Published • 24
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
Paper • 2509.22186 • Published • 175
Unlimited OCR Works
Paper • 2606.23050 • Published • 54