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.
As world-action model papers proliferate, a shared testbed that holds the backbone fixed and varies one design choice at a time can shift the field from raw success-rate races toward explaining why a design works, and separable action modules hint at robot brains that can be iterated in pieces.