DreamTrue：透過反事實後訓練實現忠實動作跟隨的機械人世界模型
DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training
DreamTrue 是一個多視角、跨具身的機械人世界模型，結合反事實後訓練，在 AgiBot 上達到最先進的動作跟隨表現。其經人手評估的交互缺陷率由 48.12% 降至 6.25%。DreamTrue 並在 AgiBot World Challenge 2026 的世界模型賽道排名第一。
Published on Oct 8
Authors:
,
,
,
,
,
,
,
Abstract
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.
View arXiv page View PDF Project page GitHub 0 Add to collection
Get this paper in your agent:
hf papers read 2610.12468
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.12468 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.12468 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.12468 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源：HuggingFace Daily Papers（社區熱門論文） · huggingface.co