SyncAI.news, a Varaisys broadcasting
PhysResponse: Probing the Physics of Video Generation with Controlled Interventions
YL

Yuhan Li, Shuran Zhang, Haixin Tian, Baonuo Rao, Weipeng Li, Yujia Hou, Zhenyu Wang, Zijun Wang, Luoyang Lin, Lijing Luo, Jiehui Huang, Kaiyuan Yang, Jingbin Tan, Panwen Hu, Xiaodan Liang

· 1 min read

ResearcharXiv cs.CV

PhysResponse: Probing the Physics of Video Generation with Controlled Interventions

arXiv:2611.24419v1 Announce Type: new Abstract: Video generation models are increasingly viewed as world simulators, which requires not only plausible motion but dynamics that respond correctly to specified physical parameters. Existing models, datasets and benchmarks, however, largely target physical plausibility, leaving this physical parameter responsiveness insufficiently explored. We introduce PhysResponse, a benchmark that measures it at two levels: scene-conditioned simulator inversion recovers the effective gravity, friction and initial speed of generated motion, and event evaluation tests outcomes near and across critical transitions. Evaluating ten image-to-video models, we find that even the lowest parameter errors exceed those of physically correct videos by over an order of magnitude, that models rarely reproduce both outcomes of a transition pair, and that the two levels expose complementary failures that visual metrics such as PSNR miss. To supply the missing training signal, we construct 72,000 simulated videos of 20 multi-object interaction types with controlled parameters; fine-tuning on them lowers parameter errors, even on held-out interaction types, and transfers to real videos and an external physics benchmark. Continued training with a numerical encoder further lowers all three errors on held-out types. PhysResponse provides a foundation for world simulators that follow physical conditions, not just appearances.

Original source

This story was published by arXiv cs.CV and written by Yuhan Li, Shuran Zhang, Haixin Tian, Baonuo Rao, Weipeng Li, Yujia Hou, Zhenyu Wang, Zijun Wang, Luoyang Lin, Lijing Luo, Jiehui Huang, Kaiyuan Yang, Jingbin Tan, Panwen Hu, Xiaodan Liang. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News