# EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields

Source: [EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields](<https://www.sota2.com/research/paper/69fd6e1b5497b3b670c89471>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-09T05:00:12.752Z

Authors: Zhaoyang Yang, Yurun Jin, Lizhe Qi, Cong Huang, Kai Chen

Published: 2026-05-07T13:06:19.000Z

## Abstract

Pretrained video diffusion models provide powerful spatiotemporal generative priors, making them a natural foundation for robotic world models. While recent world-action models jointly optimize future videos and actions, they predominantly treat video generation as an auxiliary representation for policy learning. Consequently, they insufficiently explore the inverse problem: leveraging action signals to guide video synthesis, thereby often failing to preserve precise robot spatial geometry and fine-grained robot-object interaction dynamics in the generated rollouts. To bridge this gap, we present EA-WM, an Event-Aware Generative World Model that effectively closes the loop between kinematic control and visual perception. Rather than injecting joint or end-effector actions as abstract, low-dimensional tokens, EA-WM projects actions and kinematic states directly into the target camera view as Structured Kinematic-to-Visual Action Fields. To fully exploit this geometrically grounded representation, we introduce event-aware bidirectional fusion blocks that modulate cross-branch attention, capturing object state changes and interaction dynamics. Evaluated on the comprehensive WorldArena benchmark, EA-WM achieves state-of-the-art performance, outperforming existing baselines by a significant margin.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Video Generation on WorldArena](<https://www.sota2.com/research/sota/video-generation-on-worldarena.md>): Video Generation; WorldArena; Interaction Quality: 68.2.

- [Embodied World Modeling on WorldArena Robotwin](<https://www.sota2.com/research/sota/embodied-world-modeling-on-worldarena-robotwin.md>): Embodied World Modeling; WorldArena Robotwin; Interaction Quality Score: 0.682.

- [Video Perception on WorldArena](<https://www.sota2.com/research/sota/video-perception-on-worldarena.md>): Video Perception; WorldArena; Img Score: 0.364.

- [World Modeling on WorldArena (test)](<https://www.sota2.com/research/sota/world-modeling-on-worldarena-test.md>): World Modeling; WorldArena (test); Image Quality: 36.4.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.06192>)

[PDF](<https://arxiv.org/pdf/2605.06192.pdf>)
