Inference-time Physics Alignment of Video Generative Models with Latent World Models

作者：Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich, Nicolas Beltran-Velez, Melissa Hall, Reyhane Askari-Hemmat, Xiaochuang Han, Nicolas Ballas, Michal Drozdzal, Adriana Romero-Soriano · 会议/期刊：arXiv preprint 2026 · 方向：视频数据引擎 · 发布日期：2026-01-15