$\omega$-EVA: Envision, Verify, and Act with Latent Interactive World Models

Published June 25, 2026 · Category: Robotics

Overview

arXiv:2606.09457v2 Announce Type: replace 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.

Source

Originally published at arxiv.org.

Related Articles

• Sampling Strategies for Robust Universal Quadrupedal Locomotion Policies
• Action ControlNet: A Lightweight Delay-Aware Adapter for Smooth Asynchronous Control in Vision-Language-Action Models
• DynaMOMA: Instantaneous Prediction of Grasp Poses for Mobile Manipulation of Dynamic Objects