Researchers from Peking University have Mission XXX Impossibleformed a small team that is aiming to “reproduce” OpenAI’s text-to-video generator Sora, according to its project page on GitHub, after the original model took GenAI to the next level following its roll out in February. Collaborating with Shenzhen-based AI firm RabbitPre, China’s top academic institution is seeking resources from the open-source community as they are “unable to conduct full training” due to a lack of video data. However, the team has developed a three-part framework – including a Video VQ-VAE, a Denoising Diffusion Transformer, and a Condition Encoder – and presented its initial progress on GitHub, with four reconstructed video demos offering different resolutions and aspect ratios, ranging from three to 24 seconds in length. [GitHub]
Related Articles
2025-06-27 06:31
898 views
NYT Connections hints and answers for February 1: Tips to solve 'Connections' #601.
Connectionsis the one of the most popular New York Times word games that's captured the public's att
Read More
2025-06-27 05:40
2523 views
The People's Report Cards hold the world's governments accountable
A year ago, the leaders of the world made a promise to the seven-and-a-half billion people on this p
Read More
2025-06-27 05:33
587 views
Sterling K. Brown wins Emmy for portraying Chris Darden in 'People v. O.J.'
The Emmy verdict is in, with Sterling K. Brown emerging as winner of Best Supporting actor in a limi
Read More