Stanford's Fei-Fei Li team open-sources OpenWAM, a unified world-action model framework for robots
jiqizhixin · x · 2026-10-16
Stanford researchers including Fei-Fei Li, Jiajun Wu, and Ehsan Adeli released OpenWAM, an open world-action model framework that treats video models as the robot's brain. It addresses the field's confounding habit of changing video backbone, data, interaction design, and inference pipeline all at once by providing a unified, open benchmark. OpenWAM uses causal video pretraining (built on Wan2.2 plus 10k+ hours of robot/human interaction video) to encode physical priors, a shared Mixture-of-Transformers coupling video and action streams, configurable video-action interaction modes, and local-context inverse/forward dynamics models for translating predictions into actions.
More from Embodied
- Robotics LLMs tested on 16 tasks: GPT-6 Astra hits 17.2% success vs Fable's 9.1% — pabbeel · 2026-10-16
- WEDGE paper generates training environments conditioned on navigation agent failures — _akhaliq · 2026-10-16
- Viral meme nails AI's irony: it can write symphonies but can't do the dishes — briannekimmel · 2026-10-16
- Knödel Watch: animated vocabulary cards on ESP32-S3, open-sourced 4 days after unboxing — alexcovo_eth · 2026-10-16
- NVIDIA RTX Spark PC launches tomorrow with global events and strong early reviews — NVIDIA Blog · 2026-10-16
- SlipSense fuses pressure and vibration for 23ms zero-shot robotic slip detection — micoolcho · 2026-10-16