AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

WorldReward: Reward Modeling for Camera-Conditioned World Models

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Camera-conditioned world models generate interactive videos in which commanded actions should induce the expected scene changes while appearance, geometry, and temporal dynamics remain coherent. Existing rewards assess these requirements separately: geometry-based rewards estimate trajectory execution but cannot judge the visual quality of the executed motion, whereas image-based rewards measure frame quality without capturing action execution or temporal dynamics. We posit that a vision-language model (VLM) offers a shared reasoning space for relating actions to their visual outcomes. However

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-21T04:51:57.792Z. This is not the publication date.