World model
All-clean actionsPredict the effect of known actions.
OneWM
One causal model learns to predict the world
and act in it.

THE FILM
OneWM in 2 minutes 52 seconds.
English narration · 1080p
This is OneWM: one model that learns to imagine the world, and to act in it.
Robots need two kinds of understanding. A world model asks: if I take this action, what happens next? A policy asks the reverse: given what I see, what should I do? These are usually learned apart. So, can learning one make the other better, in both directions?
That's where OneWM comes in. It brings world prediction and action generation into one causal framework, where actions play two roles: a condition that says what will be done, and a target to learn.
Inside, a video expert and an action expert share joint causal attention, and both read the task instruction.
That attention follows time. Future frames read the past and their aligned actions, while actions read only what has been observed, never the future.
Training mixes three action regimes. With every action given, the model learns their visual consequences. With only the first few, it completes the rest. With none, it generates every action from what it sees.
One objective learns future video and unknown actions together.
So, does learning the world help the robot act? Under matched comparisons, yes. Success rises on all three benchmarks, with the largest gain, over eight points, on the most challenging one.
On a real robot, across three tasks, overall success climbs from 48.9 to 66.7 percent.
Now, the other direction. Given the same actions, does learning to act help the model predict the future?
It does. OneWM improves all three image-quality metrics on every benchmark, so predicted futures stay closer to reality.
Put the two together, and OneWM can dream. From a single observation, it predicts actions, imagines their effects, and feeds that imagined view back in to act again. Sixteen rounds, over five hundred actions, all inside its own imagination.
OneWM. Understanding the world by learning to act in it. Explore the paper and the project page.
For the exact baselines and scope of the video’s claims, see the matched comparisons below and the paper. The Dream–Act examples demonstrate imagined progression, not closed-loop simulator success.
Download English captionsWorld and action modeling are closely related, yet their reciprocal benefits under unified causal training remain unclear. We introduce OneWM, a simple framework for unified causal training that treats actions as both conditions for world prediction and targets for policy learning within a shared video-action architecture. Using this framework, we investigate whether learning forward dynamics conditioned on specified actions improves action learning, and whether learning to generate actions in turn improves action-conditioned world modeling. We use LIBERO, LIBERO-Plus, and RoboCasa365 as embodied testbeds to evaluate both policy learning and world modeling, complemented by real-world policy experiments. Learning the visual consequences of specified actions improves policy performance and generalization across changing scenes. In turn, action learning improves multi-view world-prediction fidelity under the same architecture. Together, these results answer both questions positively, supporting reciprocal benefits between world modeling and action generation under unified causal training.
01 / THE IDEA
A world model learns what happens when a robot acts.
A policy learns which action to take.
Can learning one help the other?
Predict the effect of known actions.
Learn world prediction and action together.
Predict with noisy action conditions.
Predict without reading action tokens.
Clean-action prediction strengthens control and generalization.
Learning actions improves future-video prediction.
02 / HOW IT WORKS
Actions are both conditions for prediction
and targets for learning.
A clean prefix conditions future-video prediction and denoising of the remaining action suffix.
03 / IN THE REAL WORLD
Precise placement. Careful alignment.
Everyday manipulation, on a real robot.
Full robot recordings · Original speed · Silent
04 / IMAGINED FUTURES
Watch how the predicted future follows a sequence of actions.
Loading recorded examples…
Same actions, two futures. Drag to rotate the recorded trajectory; scrub to follow the motion.
Each clip starts with an observed frame, followed by eight predictions. Reference video and conditioning actions come from the same sample. The 3D path shows recorded end-effector positions in metres; it is not a predicted path. Action values are raw controller commands, not displacements in metres. Sample details include timing and model information.
05 / A NEW FINDING
Give OneWM an initial observation and a task. It predicts the next actions, imagines their consequences, then uses its own predicted view to decide what to do next.
After the first observation, OneWM sees only what it imagines.
OneWM · LIBERO
32 controls from the current view.
8 future frames, guided by those actions.
Feed it back. The next round begins.
Unified causal training connects policy and world prediction: OneWM can carry a task forward inside a world it generates itself.
Selected task:
16 rounds · 512 predicted actions · 25.6 s in imagination
Each LIBERO example starts from one dual-camera observation and a task instruction. The same OneWM checkpoint alternates action prediction and action-conditioned video prediction. Every later visual input is its own last generated frame; no later recorded observations or recorded actions enter the loop.
The animation reveals each saved 32-action prediction in temporal order, then plays its corresponding eight future frames. The 3D path accumulates the predicted translation commands within each round; it is a relative control path, not a measured end-effector trajectory. Values use the experiment’s denormalized actions. The pauses illustrate the loop, not inference speed.
All six examples retain the full 16 rounds. This experiment evaluates imagined task progression. Simulator execution and automatic completion detection are outside this experiment; long rollouts can show drift and generation artifacts.
06 / WHAT WE FIND
Matched comparisons support reciprocal benefits.
Policy success
vs. WAMmaskBetter PSNR, SSIM & LPIPS
Across all three benchmarks, against the same-architecture world model.Real-world success: 48.9% → 66.7%, WAMmask → OneWM. Three tasks; 15 trials per task and model.
World prediction, PSNR ↑: LIBERO 22.33 → 22.95 · LIBERO-Plus 20.54 → 21.05 · RoboCasa365 24.72 → 25.21. Same MoT architecture, WM → OneWM.
Selected paper results. Distributional metrics and individual perturbation categories show a more nuanced picture.
Explore the architecture, experiments, and findings in the paper.
Read the paperIf you find this work useful, please cite: Download BibTeX
@article{OneWM,
title={Can World and Action Modeling Benefit Each Other under Unified Causal Training?},
author={Yue Su and Bokai Lin and Xinkai Wang and Chubin Zhang and Xiangnan Wu and Kuan Zhang and Weiyang Jin and Jiwen Yu and Yiming Li and Cewu Lu and Lixin Yang and Xihui Liu},
journal={arXiv preprint arXiv:2610.21095},
year={2026},
eprint={2610.21095},
archivePrefix={arXiv},
primaryClass={cs.CV},
doi={10.48550/arXiv.2610.21095},
url={https://arxiv.org/abs/2610.21095}
}