Article

POD-RoPE: Physical Observation Distribution Rotary Position Encoding for Embodied AI

The authors propose POD-RoPE, which represents a token's observation footprint as a distribution over camera centers, viewing directions, and sampling times, uses expected rotations to encode relative relationships between distributions, and reduces to pointwise RoPE when each distribution collapses to a single point.

Part of the event: POD-RoPE: Physical Observation Distribution Positional Encoding for Embodied AI

This page provides a summary and source link only.