Article

Retrieve to Act: Improving VLA Execution Robustness with Motion Primitive Graph Retrieval

The authors propose Retrieve to Act (R2A), a test-time scaling framework that organizes successful demonstrations into an offline spatiotemporal motion primitive graph. At inference, a query-dependent graph neural network locates the current execution state and retrieves structurally compatible future motion primitives, which are then fused with the frozen VLA's predicted actions through dimension-wise gating.

Part of the event: R2A Uses Motion Primitive Graph Retrieval to Improve VLA Robustness

This page provides a summary and source link only.