← Back to Benchmarks
simmediummanipulation-datametric · varies
ReWorld: Multi-Dimensional Reward Modeling for Embodied World Models
Description
Recently, video-based world models that learn to simulate the dynamics have gained increasing attention in robot learning. However, current approaches primarily emphasize visual generative quality while overlooking physical fidelity, dynamic consistency, and task logic, especially for contact-rich manipulation tasks, which limits their applicability to downstream tasks. To this end, we introduce ReWorld, a framework aimed to employ reinforcement learning to align the video-based embodied world m