Awesome World Model Hub Papers · Datasets · Projects
← Back to papers

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

arXiv 26.3 2026 71.1 method, application

TLDR

EVA uses inverse dynamics rewards to align video world models with executable robot actions, addressing the executability gap via RL post-training.

Reasoning

The paper clearly identifies a practical problem (executability gap) and proposes a novel RL-based alignment method using inverse dynamics as reward. Strengths include direct use of real robot trajectories and robustness to visual artifacts. Weaknesses include potential embodiment specificity and reliance on pre-collected real data.

Read-first score

Read-first score 71.1, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 55.

Recency 8%
100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Topical relevance 42%
78.6

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Methodology quality 25%
70

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark,experiment,result

Reproducibility 25%
50

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=artifact,code,github

Field roles

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 85.

Keyword Scores

world model
10
video world model
10
generative world model
9
world dynamics prediction
8
world simulator
7
model-based reinforcement learning world model
6
interactive world model
5

Deep Analysis

Innovations

  • Leveraging the executability gap as a training signal for video world models
  • Repurposing an inverse dynamics model (IDM) trained on real robot trajectories as a reward model for video alignment
  • Reinforcement-learning post-training framework (EVA) to align video world models with executable robot actions

Methodology

EVA is a reinforcement-learning post-training framework that trains an inverse dynamics model (IDM) on real robot trajectories and uses it as a reward model to evaluate generated videos through the action sequences they induce. The reward encourages smooth motions (measured by velocity, acceleration, and jerk) and penalizes actions that violate embodiment constraints, even when generated videos contain severe visual artifacts.

Key Results

Experiments on the RoboTwin benchmark and a real bimanual robot show that EVA reduces embodiment-specific artifacts in generated rollouts and improves downstream task execution success.

Tags