Long-WAM: Scaling the Context of World-Action Models
Long-WAM: Scaling the Context of World-Action Models
This research presents Long-WAM, a model-system framework that scales the context of causal world-action models under real-time control constraints. By using autoregressive pretraining, the model improves task success rates on benchmarks like RoboCasa GR-1 and LIBERO-Long. It also supports real-time deployment on hardware platforms, enabling dynamic and long-horizon manipulation tasks.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
context
0–19.2 seconds
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
far more when the video foundation is pretrained autoregressively (AR). We first learn causal prediction from robot and egocentric videos without action labels, then preserve this history-to-future structure during world-action adaptation. On RoboCasa GR-1, increasing context from 0.0 to 19.2 seconds raises success from 63.3% to 78.7%, whereas a bidirectionally pretrained initialization shows no net gain; robot-domai
Open source S3
atent prediction, takes 107.4 ms. Real-time deployment on Unitree G1 and YAM supports dynamic and long-horizon manipulation, including 95% success on dynamic cup stacking, where Pi0.5 and Fast-WAM succeed in none of 20 trials. As a memory-informed executor, Long-WAM also complements higher-level planning in composite tasks.
Open source S5
n AR pretraining further raises peak success on GR-1 and LIBERO-Long. Long-WAM also achieves the best results among compared methods on LIBERO-Long, RoboTwin 2.0, and DOMINO. Streaming observation encoding, asynchronous execution, and hardware-specific acceleration enable deployment on RTX 5090, DGX Spark, and Jetson AGX Thor without dropping future prediction; on RTX 5090, each action chunk, including future-video l
Open source S4
Source：arXiv Robotics — research abstracts · arxiv.org