galbot · 6 records

dateidtitleauthorsvenue↑
2026-11-162611.21607ScaleVLA: Scaling Vision-Language-Action Models to 552 Billion ParametersRuixi Yu et al.arXiv36
2026-10-202610.26848Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policyZekai Li et al.arXiv24
2026-10-012609.38537Systematically Exploring the Capabilities of GPT-6 Astra as Embodied PoliciesGalbot Team et al.arXiv21
2026-08-172608.13555HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking BenchmarkDairu Liu et al.arXiv18
2026-06-082606.06953LIMMT: Less is More for Motion TrackingYu Guan et al.arXiv14
2026-06-032606.03985Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion TrackingZekun Qi et al.arXiv41