We conduct a systematic study to investigate whether video generation is able to learn physical laws from videos, leveraging data and model scaling.
Bingyi Kang* Yang Yue* Rui Lu Zhijie Lin Yang Zhao Kaixin Wang Gao Huang Jiashi Feng Bytedance Research *Equal Contribution, in alphabetical order
👉What? We study whether video generation model is able to learn and stick to physical laws.
👉Why? OpenAI’s Sora highlights the potential of video generation for developing world models that adhere to fundamental physical laws, according to the following quotation: