EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards

arXiv:2603.17808 · cs.RO, cs.AI · Submitted 2026-03-18 · Read on arXiv

cs.RO, cs.AI

Submitted: 2026-03-18

Updated: 2026-10-18

Comments: Project page: https://eva-project-page.github.io/

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• World Model — 4× in this paper · explained in 7 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Executable Video Alignment — 1× in this paper
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies