Search papers, labs, and topics across Lattice.
3
0
3
Robotic world-action models do not need pretrained internet video backbones to scale: training native planning and dynamics modules from scratch across 30,000 hours unlocks strong zero-shot manipulation and drives a 17.7-point gain on an embodiment comprising under 2% of the data.
$\tau_0$-WM outperforms traditional models by seamlessly integrating action prediction and evaluation, leading to superior performance in complex robotic tasks.
Scaling up robot data and closing the loop with state decoding and automated reward scoring allows a 2B parameter video world simulator to outperform larger, dedicated robotic world models in real-world policy transfer.
