Hi! I am Aleksey Rybakov, Product Owner at Sber ARVR Lab. 

And before telling you what we have achieved, let me explain the meaning of this article’s heading. Or more so, explain the word “metauniverse”. This term was well-described by Mark Zuckerburg: “Metauniverse is internet implemented, where instead of looking at internet, you are inside of it.” Like a parallel universe, which you can enter yourself with AR/VR gadgets or through a 3D-avatar.

In other words, a metauniverse is simultaneously a virtual space and a way of engaging with its objects without the common “screen + keybord/mouse/sensor” medium. 

And yes, metauniverses are here. But to get into one, you’ll need a few things. First, you need to know where to look. We will talk about that later when depicting a curious case in Moscow. Second, you need a technology that will help connect the virtual world with the real one. We will talk about that as well. 

Now, let me introduce: VPS.

Multimodality has led the pack in machine learning in 2021. Neural networks are wolfing down images, text, speech and music all at the same time.  OpenAI is, as usual, top dog, but as if in defiance of their name, they are in no hurry to share their models openly.  At the beginning of the year, the company presented the DALL-E neural network, which generates 256x256 pixel images in answer to a written request.  Descriptions of it can be found as articles on arXiv and examples on their blog.  

As soon as DALL-E flushed out of the bushes, Chinese researchers got on its tail.  Their open-source CogView neural network does the same trick of generating images from text.  But what about here in Russia? One might say that “investigate, master, and train” is our engineering motto.  Well, we caught the scent, and today we can say that we created from scratch a complete pipeline for generating images from descriptive textual input written in Russian.

In this article we present the ruDALL-E XL model, an open-source text-to-image transformer with 1.3 billion parameters as well as ruDALL-E XXL model, an text-to-image transformer with 12.0 billion parameters which is available in DataHub SberCloud, and several other satellite models.

Instruments for Apple's Xcode is a tool for performance analysis of an iOS application. In 2018 Apple introduced Custom Instruments — an opportunity to expand the standard set of instruments for application profiling. When existing tools are not enough, you can create new ones yourself — it will collect, analyze and display the data the way you need.