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 15 days ago • 85
LongVie 2: Multimodal Controllable Ultra-Long Video World Model Paper • 2512.13604 • Published 23 days ago • 72
Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction Paper • 2512.04987 • Published Dec 4, 2025 • 77
Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction Paper • 2512.04987 • Published Dec 4, 2025 • 77