PulseAugur
LIVE 21:00:52
tool · [1 source] ·

SONIC model scales humanoid robot control with motion tracking

Researchers have developed SONIC, a large-scale foundation model for humanoid robot control that significantly surpasses previous models in size and capability. By treating motion tracking as a scalable task and leveraging extensive motion-capture data, SONIC learns human motion priors without manual reward engineering. This model demonstrates utility in real-time kinematic planning for tasks like navigation and supports unified token spaces for VR teleoperation and vision-language-action models, enabling complex loco-manipulation. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Demonstrates that scaling models and data can lead to more generalist and robust humanoid robot control, potentially accelerating autonomous applications.

RANK_REASON The cluster contains a research paper detailing a new AI model and its capabilities. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

COVERAGE [1]

  1. arXiv cs.CV TIER_1 · Zhengyi Luo, Ye Yuan, Tingwu Wang, Chenran Li, Fernando Casta\~neda, Sirui Chen, Zi-Ang Cao, Jiefeng Li, David Minor, Qingwei Ben, Jinhyung Park, David Sami, Zi Wang, Xingye Da, Runyu Ding, Cyrus Hogg, Lina Song, Edy Lim, Eugene Jeong, Tairan He, Haoru X… ·

    SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control

    arXiv:2511.07820v3 Announce Type: replace-cross Abstract: Despite the rise of billion-parameter foundation models trained across thousands of GPUs, similar scaling gains have not been shown for humanoid control. Current neural controllers for humanoids remain modest in size, targ…