aiqbench analysis
This research introduces $\omega$-EVA, a latent interactive world model that integrates an "Envision–Verify–Act" loop to allow embodied policies to inspect imagined consequences before executing actions. By maintaining consequence reasoning within compact latent feature space rather than generating full future video sequences at inference, the method achieves significant efficiency gains while improving performance across diverse robotic manipulation tasks without requiring additional robot-data pretraining.
$\omega$-EVA: Envision, Verify, and Act with Latent Interactive World Models
arXiv:2606.09457v1 Announce Type: new Abstract: Embodied policies typically map current observations directly to actions, leaving candidate-action consequences implicit. World models provide predictive supervision, representations, or external simulation, but rarely let a policy inspect the imagined consequence of its own proposal before acting. We introduce $\omega$-EVA, a latent interactive world model that realizes an Envision--Verify--Act loop for embodied action generation. Its three-stage framework learns action-conditioned latent dynamics, trains a language-conditioned flow policy on dynamics-aware visual representations, and feeds the policy's proposal back through the world model. A tri-branch refiner jointly reasons over the current state, proposal-conditioned future, and proposed action to produce the final action chunk. Because consequence reasoning remains in latent feature space, $\omega$-EVA avoids generating future videos at inference. Evaluations across diverse single-arm, bimanual, long-horizon, and perturbed simulation settings show that the complete interaction pipeline consistently improves the proposal policy, while latent diagnostics indicate meaningful action-conditioned future structure. With approximately 1.2B parameters and no additional robot-data pretraining, $\omega$-EVA demonstrates a compact and competitive performance--scale--data trade-off, making the world model an active action-feedback module rather than a passive predictor.
Abstract: Embodied policies typically map current observations directly to actions, leaving candidate-action consequences implicit. World models provide predictive supervision, representations, or external simulation, but rarely let a policy inspect the imagined consequence of its own proposal before acting. We introduce $\omega$-EVA, a latent interactive world model that realizes an Envision--Verify--Act loop for embodied action generation. Its three-stage framework learns action-conditioned latent dynamics, trains a language-conditioned flow policy on dynamics-aware visual representations, and feeds the policy's proposal back through the world model. A tri-branch refiner jointly reasons over the current state, proposal-conditioned future, and proposed action to produce the final action chunk. Because consequence reasoning remains in latent feature space, $\omega$-EVA avoids generating future videos at inference. Evaluations across diverse single-arm, bimanual, long-horizon, and perturbed simulation settings show that the complete interaction pipeline consistently improves the proposal policy, while latent diagnostics indicate meaningful action-conditioned future structure. With approximately 1.2B parameters and no additional robot-data pretraining, $\omega$-EVA demonstrates a compact and competitive performance--scale--data trade-off, making the world model an active action-feedback module rather than a passive predictor.
Robotics (cs.RO)
arXiv:2606.09457 [cs.RO]
(or arXiv:2606.09457v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.09457 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 268 words
Related coverage
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · Sep 25, 2026
[AINews] The Future of Latent Space
Latent Space · Sep 25, 2026
[AINews] not much happened today
Latent Space · Oct 3, 2026
[AINews] Opus 5.5 is good at explainer videos
Latent Space · Sep 29, 2026