The performance of artificial intelligence (AI) tools, including large computational models for natural language processing (NLP) and computer vision algorithms, has been rapidly improving over the past decades. One reason for this is that datasets to train these algorithms have exponentially grown, collecting hundreds of thousands of images and texts often collected from the internet.

Training data for robot control and planning algorithms, on the other hand, remains far less abundant, in part because acquiring it is not as straightforward...

In 2021, NASA’s Perseverance rover landed in the Jezero Crater on Mars. For the next three years, this astrobiology mission collected soil and rock samples from the crater floor for eventual return to Earth. The analysis of these samples is expected to reveal much about Mars’ past and how it transitioned from being a warmer, wetter place to the frigid and desiccated place we know today. Unfortunately, budget cuts have placed the future of the proposed NASA-ESA Mars Sample Return (MSR) mission in doubt.

As a result, NASA recently announced that it was seeking proposals for more cost-effective and rapid methods of bringing the samples home. This will consist of three studies by NASA and the Johns Hopkins University Applied Physics Laboratory (JHUAPL).

In addition, NASA has selecte...

Scientists at Weill Cornell Medicine discovered a previously unknown link between two key pathways that regulate the immune system in mammals — a finding that impacts our understanding of chronic inflammatory bowel diseases (IBD). This family of disorders severely impacts the health and quality of life of more than 2 million people in the United States.

The immune system has many pathways to protect the body from infection, but sometimes an overactive immune response results in autoimmune diseases including IBD, psoriasis, rheumatoid arthritis and multiple scler...

Researchers have developed a technique that allows artificial intelligence (AI) programs to better map three-dimensional spaces using two-dimensional images captured by multiple cameras. Because the technique works effectively with limited computational resources, it holds promise for improving the navigation of autonomous vehicles.

“Most autonomous vehicles use powerful AI programs called vision transformers to take 2D images from multiple cameras and create a representation of the 3D space around the vehicle,” says Tianfu Wu, corresponding author of a paper on the work and an associate professor of electrical and computer engineering at North Carolina State University...