No AI summary available for this article.
Why It Matters
Real-time robot control demands enough visual history to infer motion and task progress, but processing that history can delay action.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Real-time robot control demands enough visual history to infer motion and task progress, but processing that history can delay action. We present Long-WAM, a model-system framework for scaling the context of causal world-action models under real-time control constraints. Our central finding is that access to history is not the same as using it: longer histories pay off 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...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2610.10528v1 · Indexed about 2 hours ago