By submitting the form, I give my consent for the processing
of my personal data according to this agreement

ITMO at a Glance

Search by tag «AI Models» 4 results

  • ITMO Researchers Present World’s First AI Model for Supersensitive Optics Design

    Scientists from ITMO’s Faculty of Physics have developed MetaDiT, a generative model for automated design of metasurfaces – superthin optical elements that control light at the nanolevel. The model selects not just the nanostructure’s pattern in an elementary cell but also the key numeric parameters: a metaatom’s thickness, its refraction index, and lattice period – the distance between neighboring elements. With this approach, it’s possible to search for more accurate and versatile designs of flat optics for VR devices, sensors, medical equipment, and photon chips. This project was completed at the joint research center in Qingdao, while the corresponding paper has been accepted to AAAI, one of the leading conferences on AI.

    01.07.2026

  • Tatar AI Editor Developed by ITMO Students

    A team of students from ITMO University and HSE University created an AI-powered “detoxification” tool for the Tatar language that automatically converts rude and harmful messages into neutral ones. The solution brought the team 150,000 rubles and first place at the online hackathon AI ZAMAN HACK.

    22.12.2025

  • AI Urban Planning Platform Developed at ITMO

    Prosto.R, an AI platform created by ITMO scientists, is a fast and affordable way to evaluate and predict urban development based on available data. For instance, the system can analyze urban traffic, quality of life, and environmental quality, as well as a given area’s urban development potential. Among the platform’s potential beneficiaries are governmental bodies, property developers, and investors.

    28.05.2025

  • AI Tool to Facilitate Mineral Processing Developed at ITMO

    Students of ITMO’s Computer Technologies Laboratory have created a series of AI models for processing of clumped texture images. AI models tend to have a hard time “seeing” the borders of objects – for instance, telling one type of mineral from another – but now they can label 600 images in an hour. The new open-source solution can be used to measure the size and distribution of various objects (granulometry) in a variety of fields: examples include precious and colored metals in mining, granular materials and crystals in food or agricultural industries, as well as oil refining.

    16.05.2025