Slow-Fast Architecture for Video Multi-Modal Large Language Models Paper • 2504.01328 • Published 6 days ago • 1 • 1
Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources Paper • 2504.00595 • Published 6 days ago • 33 • 7
Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources Paper • 2504.00595 • Published 6 days ago • 33 • 7
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper • 2503.11576 • Published 24 days ago • 87 • 10
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper • 2503.11576 • Published 24 days ago • 87 • 10