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 5 days ago • 85
LongVie 2: Multimodal Controllable Ultra-Long Video World Model Paper • 2512.13604 • Published 13 days ago • 71
Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction Paper • 2512.04987 • Published 24 days ago • 75
BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping Paper • 2510.18927 • Published Oct 21 • 83