Tempered Self-Similarity Alignment for Physically Plausible Video Generation 事件

Tempered Self-Similarity Alignment for Physically Plausible Video Generation arXiv:2605.24962v1 Announce Type: new Abstract: Despite remarkable advances in video generative models, they still struggle to generate physically realistic videos, frequently exhibiting appearance drift, implausible motion, and temporal inconsistencies. In this work, we address this limitation by transferring relational knowledge encoded in spatio-temporal self-similarity (STSS) from visual foundation models into vide