view article Article Nemotron 3 Nano \- A new Standard for Efficient, Open, and Intelligent Agentic Models 27 days ago • 104
MobileCLIP Models + DataCompDR Data Collection MobileCLIP: Mobile-friendly image-text models with SOTA zero-shot capabilities. DataCompDR: Improved datasets for training image-text SOTA models. • 25 items • Updated Aug 26, 2025 • 37
EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture Paper • 2512.04810 • Published Dec 4, 2025 • 25
The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain Paper • 2509.26507 • Published Sep 30, 2025 • 544
Learning Transferable Visual Models From Natural Language Supervision Paper • 2103.00020 • Published Feb 26, 2021 • 19