Cosmos 3 Nano

Headlines · 2

1. Oct 22
   NVIDIA Expands Cosmos World-Model Platform With Training Tools and Blueprints

   NVIDIA expanded its Cosmos platform with new training tools, simulation checkpoints and Cosmos Data Factory blueprints aimed at developers building world models for physical AI. The company said Data Factory now offers five cloud-native blueprints available through GitHub, Microsoft Azure, Nebius and CoreWeave, while new Cosmos 3 Nano variants support policy testing in repeatable multiview, multisensor simulations. NVIDIA also said updated Cosmos 3 NIM microservices deliver up to 2x faster inference in validated configurations, and it reported that the Cosmos platform ranks in the top five on six open-model leaderboards—a ranking not independently verified in the supplied material.

   NVIDIA Blog · 🔥 0
2. Oct 8
   Stanford's Fei-Fei Li team open-sources OpenWAM world-action model framework

   A Stanford team including Fei-Fei Li, Jiajun Wu and Ehsan Adeli published OpenWAM, an open framework for composable world-action models that aims to disentangle the many ways video prediction and action generation can be coupled in this emerging class of robot policies. OpenWAM starts from Alibaba's open Wan2.2-5B video model, continues pretraining on roughly 3.34 million robot-and-human interaction videos (nominally about 14,600 hours) for 14 days on 32 B200 GPUs, then joins a 5B video expert with a 2B action expert via a shared Mixture-of-Transformers architecture with four configurable interaction orders (VTA, ATV, Joint, Decoupled). The authors report 98.6% average success for VTA across the four LIBERO subsets and 92.1% / 91.9% average success for VTA and Joint on three real dual-arm Franka FR3 tasks, plus a LIBERO-Long-CF counterfactual dataset; training, evaluation and composition code and pretrained video weights are open-sourced.

   36氪 人工智能 · 🔥 0

Experience and discussion from the community

Share my Cosmos 3 Nano experienceAsk about Cosmos 3 Nano