cs.RONov 18, 2026

Render the Robot, Generate the World: One Video World Model Across Embodiments

Authors: Yash Jangir, Karan Mirakhor, Renos Zabounidis, Muhammad Zubair Irshad, Sergey Zakharov, Yonatan Bisk, Homanga Bharadhwaj

Organizations: Johns Hopkins University · Carnegie Mellon University · Toyota Research Institute

Abstract

Predicting the consequences of an agent's actions requires modeling both the body's motion and the environment's response. Most video world models attempt to learn both from numerical actions, even though geometry and kinematics already specify the intended motion. We introduce Doppel, an embodiment-agnostic video world model conditioned on camera-aligned renderings of future body configurations and numerical action trajectories. By explicitly providing the intended motion, Doppel can focus on predicting object motion and interaction-driven changes in the environment. Rendered motion also provides a common visual interface across different embodiments and action spaces. To train on robot datasets without camera extrinsics, we recover camera poses and align rendered trajectories with recorded observations. We jointly train a single shared video backbone and conditioning adapter on eight datasets spanning eight robot and human embodiments, from single- and bimanual robot arms to a dexterous humanoid and human hands and bodies, using about 600 hours of video without embodiment labels. Across three robot-arm datasets, Doppel improves PSNR over action-only baselines by 1.00 dB on held-out trajectories and 1.20 dB under out-of-distribution evaluation, while predicting more consistent object motion. Training on all eight embodiments (Doppel-8) improves robot predictions over the three-robot model (Doppel-3) on four of six evaluation sets. Project page: https://doppelwm.github.io/.

Figures & tables

Appendix figures & tables26 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training

    Oct 8, 2026Junyan Li, Ruizhi Li, Yu Liu +6World Models for RoboticsAction-Conditioned World Models

  2. Robot-Factored World Models via Robot Rendering

    Jul 24, 2026Byungjun Kim, Taeksoo Kim, Hyunsoo Cha +1Action-Conditioned World ModelsCross-Embodiment Robot Learning