Skip to content
RobotWorld
← Tags

#Data Scaling (3)

WaterfallPagination
Helix 2.5 Recap: Scaling Human Data to Zero-Shot Generalization
0:09

Helix 2.5 Recap: Scaling Human Data to Zero-Shot Generalization

@CyberRobooo · 703 views · 2026-09-18
HumanoidFoundation Models
AgiBot GE-Act 2.0: A World Action Model Trained From Scratch
3:49

AgiBot GE-Act 2.0: A World Action Model Trained From Scratch

@Chinazhidx · 723 views · 2026-09-09
World-action modelsVLA
Scaling Bimanual Household Manipulation from 1,500 hours of Demonstrations to On-Policy Corrections

Scaling Bimanual Household Manipulation from 1,500 hours of Demonstrations to On-Policy Corrections

The authors release 1,500 hours of bimanual household manipulation data and train XR-2, a 5B-parameter VLA. On clothes folding, expert data lifts success from 34% to 84% before saturating, and three rounds of on-policy DAgger corrections then raise it from 58% to 93%.

Jiafeng Xu, Qi Li, Yan Shen · 732 views · Sep 3, 2026
Bimanual ManipulationVision-language-action (VLA)
Sep 3, 2026

As an Amazon Associate, we earn from qualifying purchases.