AI & ML
Learning Generalizable Hand-Object Tracking from Synthetic Demonstrations
arXiv cs.GR0 views
arXiv:2512.19583v2 Announce Type: replace-cross Abstract: We present a system for learning generalizable hand-object tracking controllers purely from synthetic data, without requiring any human demonstrations. Our approach makes two key contributions: (1) HOG, a highly efficient Hand-Object data generator that rapidly synthesizes diverse, large-scale, and uniformly distributed trajectories; and (2) HOT, a Hand-Object Tracker that bridges synthetic-to-physical transfer through reinforcement learning and interaction imitation learning. Our method extends to diverse object shapes and hand morphologies. HOT also enables cross-simulator transfer. Through extensive evaluations, we show that our approach enables dexterous hands to track challenging, long-horizon sequences including object re-arrangement and agile in-hand reorientation. These results represent a significant step toward scalable foundation controllers for manipulation that can learn entirely from simple, scalable synthetic data, breaking the data bottleneck that has long constrained progress in dexterous manipulation.
Source:https://arxiv.org/abs/2512.19583PreviousSSA-3DGS: Unsupervised Removal of Screen-Space Artifacts for 3D Gaussian SplattingNextAbacusGS: Gaussian Splatting without Per-Splat Sorting
Related posts

The UK and some other countries don’t get more Siri AI usage with iCloud+
09to5Mac

MacPaw’s Moonlock comes to iPhone, helping users detect potential scams
09to5Mac

Six new Aqara smart lights with Apple Home support and ‘spatial intelligence’
09to5Mac

Leaker claims Apple developing four models of 20th anniversary iPhone
09to5Mac

The Download: AI learns to smell and hydropower struggles
0MIT Technology Review

Nvidia isn’t selling any more AI chips to China
0The Verge