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

Junyan Li, Ruizhi Li, Yu Liu, Xiangshuo Liu, Mingchao Sun, Hongyu Pan, Mu Xu, Lue Fan, Zhaoxiang Zhang · N/A · 2026

Summary

We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction.

Abstract Summary

We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction. Training such a model on existing robot datasets faces two obstacles: imprecise calibration can impair action following, while limited coverage of unsuccessful interactions can bias predictions toward successful outcomes. To improve action following across embodiments, we render action trajectories into image-space conditions and introduce offline geometric calibration to align these conditions with the target videos. To broaden interaction coverage, we introduce counterfactual post-training, modifying recorded action trajectories and generating future videos under a wider range of actions and contact configurations. To provide feedback on these predictions without paired ground-truth futures, we construct a human-annotated video dataset covering robot, object, and interaction defects and use it to train an embodied video reward model. Its scores guide reinforcement-learning post-training toward more physically plausible interaction outcomes. On AgiBot, DreamTrue attains state-of-the-art action following, while reducing the human-assessed interaction defect rate from from 48.12% to 6.25%. Notably, our model ranks first in the world model track of the AgiBot World Challenge 2026. The project page can be found at https://brave-eai.github.io/DreamTrue.

Key Points

We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction.
Training such a model on existing robot datasets faces two obstacles: imprecise calibration can impair action following, while limited coverage of unsuccessful interactions can bias predictions toward successful outcomes.
To improve action following across embodiments, we render action trajectories into image-space conditions and introduce offline geometric calibration to align these conditions with the target videos.
To broaden interaction coverage, we introduce counterfactual post-training, modifying recorded action trajectories and generating future videos under a wider range of actions and contact configurations.
To provide feedback on these predictions without paired ground-truth futures, we construct a human-annotated video dataset covering robot, object, and interaction defects and use it to train an embodied video reward model.

Method

Given initial multi-view observations ${\bm{x}}_{0}^{1:V}$, a task instruction $\ell$, and an action sequence ${\bm{a}}_{1:T}$, we model the distribution of future videos as where $V$ is the number of camera views, $T$ is the prediction horizon, and $\theta$ denotes model parameters. Our framework consists of offline geometric calibration and two training stages.

We first refine camera parameters and optional robot mounting offsets to improve spatial alignment between robot renderings and recorded video frames.

Method — DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training — Figure 1 : Overview of DreamTrue . Camera calibration aligns robot renderings with recorded videos. Stage I learns action-conditioned prediction across embodiments, while Stage II uses video rewards for counterfactual post-training to improve interaction plausibility.

Experiments

DreamTrue is jointly trained on AgiBotWorld-Beta ( Bu et al., 2025a ) , DROID ( Khazatsky et al., 2024 ) , RoboMIND 2.0 ( Hou et al., 2025 ) , and RoboTwin 2.0 ( Chen et al., 2025 ) . After filtering, the training data contain 2,232 h of multi-view trajectories across five robot arm types in real and simulated environments ( Figure 10 , in appendix).

We evaluate future prediction on held-out episodes from these datasets.

Experiments — DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training — (a) $\mathcal{P}_{\mathrm{align}}$

Sources and Demonstrations

Figures are reproduced from Li et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.