Skip to content
← Back to Videos

R2-WAM: What Visual Representations Do World Action Models Need?

Loading video
Loading video

A controlled study of visual representations, five integration mechanisms and feature combinations for World Action Models: general-purpose representations give the broadest robustness, channel-wise joint prediction scores highest, and R2-WAM reaches 84.7% on RoboCasa GR1 Tabletop and 92.8% on RoboTwin 2.0.

Category: humanoid
Author: @ai_bites
Date: 2026-10-15T00:00:00
Duration: 93.766s

As an Amazon Associate, we earn from qualifying purchases.