VDU Research Topic This collection is for visual document related task that included the research materials, models, and dataset. SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper • 2503.11576 • Published Mar 14, 2025 • 137
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper • 2503.11576 • Published Mar 14, 2025 • 137
VDU Research Topic This collection is for visual document related task that included the research materials, models, and dataset. SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper • 2503.11576 • Published Mar 14, 2025 • 137
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper • 2503.11576 • Published Mar 14, 2025 • 137
