Skip to main content
Search

Gehao Zhang

1 related articles

Subscribe to updates
  1. arXiv

    GAM swaps language and video pretraining for a frozen 3D grounding backbone, lifting RoboTwin 2.0 randomized-scene success from 30.4% to 47.6%

    The work proposes Grounded Action Model (GAM), which builds a robot foundation model on a pretrained promptable 3D grounding model (WildDet3D), maps language, 2D point, or 2D box prompts into a shared object-centric representation (image tokens keeping target visual features plus detection tokens encoding point clouds, metric positions, and extents), and uses a multi-stream transformer (MM-DiT) with robot state history to predict action chunks; it reaches 55.3% average success across 50 RoboTwin 2.0 tasks (vs. 52.0% for Spatial Forcing), 47.6% under scene randomization (vs. 30.4% for Abot-M0), a state-of-the-art 61% average across 16 LIBERO-PRO perturbation settings (vs. 53%), 17/20 successes under visual shift on a bimanual YAM (vs. 4/20), and 64.7% in-distribution and 49.

You’re all caught up