SmolVLM: Redefining small and efficient multimodal models Paper • 2504.05299 • Published 11 days ago • 161
Llama 4 Collection Meta's new Llama 4 multimodal models, Scout & Maverick. Includes Dynamic GGUFs, 16-bit & Dynamic 4-bit uploads. Run & fine-tune them with Unsloth! • 15 items • Updated 1 day ago • 43
DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance Paper • 2504.01724 • Published 16 days ago • 62
Gemma 3 QAT Collection Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated about 4 hours ago • 123
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper • 2503.11576 • Published Mar 14 • 94
Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning Paper • 2503.15558 • Published about 1 month ago • 45
ReCamMaster: Camera-Controlled Generative Rendering from A Single Video Paper • 2503.11647 • Published Mar 14 • 134