Generating high-quality, temporally continuous videos requires a significant amount of computational resources, especially for longer time spans. The latest Diffusion Transformer model (DiTs) has made significant progress in video generation, but its reliance on larger models and more complex attention mechanisms has resulted in slower inference speeds, exacerbating the challenge. To address this issue, researchers at Meta AI have proposed a training-free method called AdaCache to accelerate video DiTs.

Another major move in the tech world! OpenAI has announced the launch of OpenAI Academy, a program aimed at investing in developers and organizations to leverage artificial intelligence (AI) to solve problems and catalyze community economic growth. The goal of this academy is to ensure that the transformative potential of AI is accessible and beneficial to diverse communities worldwide, particularly in low- and middle-income countries. Many countries' tech sectors are rapidly developing, boasting talented developers and innovative organizations, yet opportunities to access advanced training and technological resources remain limited.