SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control
Quick summary
arXiv:2511.07820v4 Announce Type: replace-cross Abstract: Despite the rise of billion-parameter foundation models trained across thousands of graphical processing units (GPUs), similar scaling gains have not been shown for humanoid control. Current neural controllers for humanoids remain modest in size, target a limited set of behaviors, and are trained on a handful of GPUs. We show that scaling model capacity, data, and compute yields a generalist humanoid controller capable of natural, robust whole-body movements. We position motion tracking as a scalable task for humanoid control, leveragin
Key takeaways
- arXiv:2511.07820v4 Announce Type: replace-cross Abstract: Despite the rise of billion-parameter foundation models trained across thousands of graphical processing units (GPUs), similar scaling gains have not been shown for humanoid control.
- Current neural controllers for humanoids remain modest in size, target a limited set of behaviors, and are trained on a handful of GPUs.
- We show that scaling model capacity, data, and compute yields a generalist humanoid controller capable of natural, robust whole-body movements.
Why it matters
“SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments