Toggle light / dark theme

Pixart-σ weak-to-strong training of diffusion transformer for 4K text-to-image generation.

PixArt-Σ

Weak-to-strong training of diffusion transformer for 4K text-to-image generation.

In this paper, we introduce PixArt-Sigma, a Diffusion Transformer model~(DiT) capable of directly generating images at 4K resolution.


The Short-Baseline Near Detector collaboration is preparing for an exciting year at the U.S. Department of Energy’s Fermi National Accelerator Laboratory. After nearly a decade of planning, prototyping and construction, the team is in the final stretch of commissioning of their detector.

In January, engineers began introducing gaseous argon into SBND to push air out of the cryostat. Now that the detector is mostly free of impurities, the team has begun filling it with liquid argon.

“We’re all excited to get to this point. It’s one of the last steps before we see our first particle tracks,” said Roberto Acciarri, the detector assembly and installation co-coordinator for SBND.

A new computer model mimics Moon dust so well that it could lead to smoother and safer Lunar robot teleoperations. The tool, developed by researchers at the University of Bristol and based at the Bristol Robotics Laboratory, could be used to train astronauts ahead of Lunar missions. Working with their industry partner, Thales Alenia Space in the UK, who has specific interest in creating working robotic systems for space applications, the team investigated a virtual version of regolith, another name for Moon dust.

Lunar regolith is of particular interest for the upcoming Lunar exploration missions planned over the next decade. From it, scientists can potentially extract valuable resources such as oxygen, rocket fuel or construction materials, to support a long-term presence on the Moon. To collect regolith, remotely operated robots emerge as a practical choice due to their lower risks and costs compared to human spaceflight.

However, operating robots over these large distances introduces large delays into the system, which make them more difficult to control. Now that the team know this simulation behaves similarly to reality, they can use it to mirror operating a robot on the Moon. This approach allows operators to control the robot without delays, providing a smoother and more efficient experience.

Researchers at the Icahn School of Medicine at Mount Sinai and others have harnessed the power of machine learning to identify key predictors of mortality in dementia patients.

The study, published in the February 28 online issue of Communications Medicine, addresses critical challenges in dementia care by pinpointing patients at high risk of near-term death and uncovers the factors that drive this risk.

Unlike previous studies that focused on diagnosing dementia, this research delves into predicting patient prognosis, shedding light on mortality risks and contributing factors in various kinds of dementia.

High-intensity exercise induces brain-protective effects that have the potential to not just slow down but possibly reverse the neurodegeneration associated with Parkinson’s disease, a new pilot study suggests.

Prior research has shown that many forms of exercise are linked to improved symptoms of Parkinson’s disease. But there has been no evidence that hitting the gym could create changes at the brain level. Now, a small proof-of-concept study involving 10 patients showed that high-intensity aerobic exercise preserved dopamine-producing neurons, the brain cells that are most vulnerable to destruction in patients with the disease.

In fact, after six months of exercise, the neurons actually had grown healthier and produced stronger dopamine signals. Dopamine is a chemical that helps brain cells communicate with one another. The researchers published their findings in npj Parkinson’s Disease on February 9.

“There’s a muon right there,” says Tioukov, pointing to a squiggly line he’s blown up using a microscope.

After months of painstaking analysis, Tioukov and his team are able to put together a three-dimensional model of that hidden burial chamber, closed to human eyes for centuries, now opened thanks to particle physics.

What seems like science fiction is also being used to peer inside the pyramids in Egypt, chambers beneath volcanoes, and even treat cancer, says Professor Giovanni De Lellis.