PixMo Collection A set of vision-language datasets built by Ai2 and used to train the Molmo family of models. Read more at https://molmo.allenai.org/blog • 10 items • Updated 6 days ago • 85
LongVie 2: Multimodal Controllable Ultra-Long Video World Model Paper • 2512.13604 • Published 14 days ago • 71
Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction Paper • 2512.04987 • Published 25 days ago • 75
Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction Paper • 2512.04987 • Published 25 days ago • 75