Computer Vision System Marries Image Recognition and Generation

Computer vision system marries image recognition and generation
A unified vision system known as Masked Generative Encoder (MAGE), developed by researchers at MIT and Google, could be useful for many things, like finding and classifying objects in an image, learning from just a few examples, generating images with specific conditions such as text or class, editing existing images, and more. Credit: Alex Shipps/MIT CSAIL via Midjourney

Computers possess two remarkable capabilities with respect to images: They can both identify them and generate them anew. Historically, these functions have stood separate, akin to the disparate acts of a chef who is good at creating dishes (generation), and a connoisseur who is good at tasting dishes (recognition).

Yet, one can’t help but wonder: What would it take to orchestrate a harmonious union between these t...

Read More

ALMA digs deeper into the Mystery of Planet Formation

Images of disks around 19 protostars, including 4 binary systems observed with ALMA. For 1 binary system, disks around the primary and secondary are presented independently (2nd line rightmost and 3rd line leftmost). Disks are presented in the order of their evolutionary sequence (the one in the upper-left corner is the youngest while the one at the lower-right corner is the oldest). The two oldest disks show faint ring-gap structures. A scale bar of 20 au (roughly the distance between the Sun and Uranus) is shown for each disk image. (Credit: ALMA (ESO/NAOJ/NRAO), N. Ohashi et al.) Original size (1.0MB)

An international research team used the Atacama Large Millimeter/submillimeter Array (ALMA) to observe disks around 19 protostars with a very high resolution to search for the earliest...

Read More

‘Smiling cat’ Sh2-284 nebula captured in new image

In the centre of this image is a large cloud, orange and red in colour, which is stretched out over the majority of the frame. The region in the top left of the cloud is particularly vivid. All around the image there are stars, in different colours of white, orange and purple. Some of these are smaller, background stars, whereas others reside in the foreground of the image, such as those in the central cluster of the nebula.
The Sh2-284 nebula, imaged by the VLT Survey Telescope

This cloud of orange and red, part of the Sh2-284 nebula, is shown here in spectacular detail using data from the VLT Survey Telescope, hosted by the European Southern Observatory (ESO). This nebula is teeming with young stars, as gas and dust within it clumps together to form new suns. If you take a look at the cloud as a whole, you might be able to make out the face of a cat, smiling down from the sky.

The Sh2-284 stellar nursery is a vast region of dust and gas and its brightest part, visible in this image, is about 150 light-years (over 1400 trillion kilometers) across. It’s located some 15,000 light-years away from Earth in the constellation Monoceros.

Nestled in the center of the brightest part of the nebula—right under...

Read More

Researchers reveal how Cells Rewrite their Fate

Researchers reveal how cells rewrite their fate
C/EBPαR35A interacts more strongly with PU.1 than unmated C/EBPα, shown here by an assay that scores the proximity of antibodies against the two proteins. Credit: Thomas Graf/Centre for Genomic Regulation

Researchers at the Centre for Genomic Regulation (CRG) in Barcelona and the Max Delbrück Center for Molecular Medicine in the Helmholtz Association in Berlin have revealed how cells accelerate changes to their identity, a process known as cell fate conversion.

The study, published today in the journal eLife, has implications for cancer research as the disease often arises from errors in cell fate decisions. The study could eventually lead to new methods of accelerating or manipulating the molecular mechanisms involved in the formation of cancer.

Central to the study is C/EBPα...

Read More