Aligning Policy Encoders with a Shape Teacher
Overview
This research introduces shape-teacher alignment, a method that uses pretrained 3D shape representations as targets for training an image-based policy encoder. By leveraging Point-MAE features from individual objects to align with corresponding image patches, the approach transfers geometric structure to the policy without altering its deployment inputs or architecture. Experiments on the LIBERO benchmark show that this method produces more structured image representations around object shapes and parts, accelerates policy convergence by 4.7x on the Object suite and 5.6x on the Spatial suite, and improves success rates—all while maintaining a purely image-based interface at deployment without requiring depth input or the shape teacher during operation.
Generated from attributed reports · Updated 2 days ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
No current evidence-backed claims. Missing information remains not reported.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalAligning Policy Encoders with a Shape Teacher
This research introduces shape-teacher alignment, a method that uses pretrained 3D shape representations as targets for training an image-based policy encoder. By leveraging Point-MAE features from individual objects to align with corresponding image patches, the approach transfers geometric structure to the policy without altering its deployment inputs or architecture. Experiments on the LIBERO benchmark show that this method produces more structured image representations around object shapes and parts, accelerates policy convergence by 4.7x on the Object suite and 5.6x on the Spatial suite, and improves success rates—all while maintaining a purely image-based interface at deployment without requiring depth input or the shape teacher during operation.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).