While text-to-video artificial intelligence models like OpenAI’s Sora are rapidly metamorphosing in front of our eyes, they have struggled to produce metamorphic videos. Simulating a tree sprouting or a flower blooming is harder for AI systems than generating other types of videos because it requires the knowledge of the physical world and can vary widely.
But now, these models have taken an evolutionary step.
Computer scientists at the University of Rochester, Peking University, University of California, Santa Cruz, and National University of Singapore developed a new AI text-to-video model that learns real-world physics knowledge from time-lapse videos. The team outlines their model, MagicTime, in a paper published in IEEE Transactions on Pattern Analysis and Machine Intelligence.
Robots often struggle to carry out tasks in places where they haven’t been trained, but a new AI model helps them clean up a mess or make a bed in unfamiliar settings
A team of engineers at the University of California San Diego is making it easier for researchers from a broad range of backgrounds to understand how different species are evolutionarily related, and support the transformative biological and medical applications that rely on these species trees. The researchers developed a scalable, automated and user-friendly tool called ROADIES that allows scientists to infer species trees directly from raw genome data, with less reliance on the domain expertise and computational resources currently required.
Species trees are critical to solidifying our understanding of how species evolved on a broad scale, but can also help find functional regions of the genome that could serve as drug targets; link physical traits to genomic changes; predict and respond to zoonotic outbreaks; and even guide conservation efforts.
In a new paper published in the journal Proceedings of the National Academy of Sciences on May 2, the researchers, led by UC San Diego electrical and computer engineering professor Yatish Turakhia, showed that ROADIES infers species trees that are comparable in quality with the state-of-the-art studies, but in a fraction of the time and effort. This paper focused on four diverse life forms— placental mammals, pomace flies, birds and budding yeasts—though ROADIES can be used for any species.
Getting a timely diagnosis of autism spectrum disorder is a major challenge, but new research from York University shows that how young adults—and potentially children—grasp objects could offer a simpler way to diagnose someone on the autism spectrum.
The work is published in the journal Autism Research.
The team, part of an international collaboration, used machine learning to analyze naturalistic hand movements—specifically, finger motions during grasping—in autistic and non-autistic individuals.
Discovering new, powerful electrolytes is one of the major bottlenecks in designing next-generation batteries for electric vehicles, phones, laptops and grid-scale energy storage.
The most stable electrolytes are not always the most conductive. The most efficient batteries are not always the most stable. And so on.
“The electrodes have to satisfy very different properties at the same time. They always conflict with each other,” said Ritesh Kumar, an Eric and Wendy Schimdt AI in Science Postdoctoral Fellow working in the Amanchukwu Lab at the University of Chicago Pritzker School of Molecular Engineering (UChicago PME).
