# GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation

arXiv: https://arxiv.org/abs/2605.27491 · HTML: https://mlsanity.com/paper/2605.27491/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2026.

## Built on by (most cited first, 9 of 9)

- [World Models for Embodied Intelligence: From Plausible to Controllable to Actionable](https://mlsanity.com/paper/2609.16697/) (2026)
- [EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots](https://mlsanity.com/paper/2607.02646/) (2026)
- [No Free Checker: A Survey of Verifiers for Robot Policies](https://mlsanity.com/paper/2609.09250/) (2026)
- [HappyWorld-Bench](https://mlsanity.com/paper/2609.24308/) (2026)
- [WorldLine: Action-Driven Visual Simulation for Robotic Manipulation](https://mlsanity.com/paper/2609.38059/) (2026)
- [KineWorld: Action-Induced Transport Fields for Embodied World Modeling](https://mlsanity.com/paper/2610.06349/) (2026)
- [DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training](https://mlsanity.com/paper/2610.12468/) (2026)
- [CASTER: Formalizing Zero-Shot Manipulation from Synthetic Videos as Constrained Optimization](https://mlsanity.com/paper/2610.12567/) (2026)
- [WorldOracle: Benchmarking Action-Conditioned World Models against Real-World Executions](https://mlsanity.com/paper/2610.18826/) (2026)

## Abstract (arXiv)

We introduce GE-Sim 2.0 (Genie Envisioner World Simulator 2.0), a closed-loop video world simulator for robotic manipulation. Building on the action-conditioned video generation framework of Genie Envisioner, GE-Sim 2.0 is re-trained on thousands of hours of real-world robot data spanning teleoperation, contact-rich interaction, and on-robot policy deployment, substantially improving action-following fidelity and trajectory coverage. On top of this foundation, three new modules close the loop from video simulation to policy learning: a state expert that decodes proprioceptive state from video latents to support next-chunk prediction by downstream VLA policies; a world judge that scores generated rollouts against task instructions, yielding machine-verifiable success signals and rewards in place of manual inspection; and an acceleration framework that delivers a 25-frame rollout in 2.3 seconds on a single H100, with up to 4* frame skipping at inference for long-horizon evaluation. GE-Sim 2.0 tops the public WorldArena leaderboard at only 2B parameters, outperforming both dedicated robotic world models and closed-source general video generators, and policies trained against its rollouts and rewards translate into measurable real-world gains, establishing GE-Sim 2.0 as a practical platform for scalable evaluation and closed-loop learning of manipulation policies.