Kineforge AI/ML model for robotics logo

Kineforge AI/ML model for robotics

Train robot brains without demos on one GPU

Artificial Intelligence Developer Tools GitHub Robots

Kineforge trains embodied control policies without human teleoperation demos. Frozen semantic priors + differentiable physics (MuJoCo MJX) + a 157K-parameter policy = training in hours on a single GPU, and CPU inference under 10ms. Structure over scale.

投票数: 4
← 投稿一覧に戻る