offline

AI Signal & Vision Meetup

When

October 16, 19:00

Format

Offline in Kyiv

Registration deadline

October 15

Fee

Donation from 500 UAH to the NGO "Reactive Post"

 pc

About

Together with the State University “Kyiv Aviation Institute,” we are launching the AI Signal & Vision Meetup — a technical event for those working at the intersection of audio processing, Computer Vision, and generative models.

We won’t touch on theoretical issues — the meetup program is focused only on practical knowledge: how to optimize models for edge devices, build production-ready systems, and apply AI to real-world tasks — from ecoacoustics to object detection.

Speakers will share case studies from their own experience and demonstrate how engineering solutions can transform into new products with dual potential — for both science and business.

Who is it for

  • Engineers in Signal Processing, Computer Vision, Embedded AI, and Machine Learning with 5+ years of experience

To participate

  • Fill in the [registration form]
  • After our confirmation, donate from 500 UAH to the NGO "Reactive Post"

What you'll gain

  • Understanding the basics of audio classification and its practical applications
  • Knowledge of how generative models help enrich training data
  • Insights into future research directions in audio and computer vision
  • An overview of AI computing evolution and the modern GPU market
  • Clear understanding of the difference between inference in the cloud and on edge devices
  • Practical tips for optimizing models for specific hardware

Speakers

Volodymyr Sydorskyi
Volodymyr Sydorskyi

Senior Computer Vision Engineer at Better Medicine, Kaggle Competitions GrandMaster, co-founder of Zvook, Deep Learning Consultant at Mantis Analytics

At Zvook, Volodymyr develops real-time sound signal detection systems. At the same time, he works as a Senior Computer Vision Engineer at Better Medicine, applying deep learning in healthcare. Volodymyr is a Kaggle Grandmaster, BirdCLEF 2025 winner, and Best Paper awardee at CLEF. He has experience in mentoring, leading ML teams, and is pursuing a PhD in Systems Analysis.

Ihor Babin
Ihor Babin

Machine Learning Engineer, Lecturer at UCU

Has over 6 years of experience in Computer Vision and Deep Learning. Author of scientific publications in the field of generative models and deep learning. Teaches the Computer Vision course as part of Generative AI at UCU, where he also mentors student and research projects. Has hands-on experience creating and deploying production-ready CV solutions both in the cloud and on edge devices.

Partners

State University "Kyiv Aviation Institute"

Program

Registration
18:30 – 19:00

AI Inference: Cloud VS Edge
19:05 – 19:45
Igor Babin

The history of AI compute, cloud development and large-scale inference, the landscape and efficiency of high-end GPUs, edge inference with considerations of privacy, cost, and offline capabilities, edge hardware and neural processing units, and hardware-aware model optimization.

Technical break
19:45 – 20:00

AI for Sound: Audio Classification in Safety and Bioacoustics
20:00 – 20:45
Volodymyr Sydorskyi

An introduction to audio classification and detection, AI-driven systems for airborne object detection, applications of audio classification in bird species recognition, data augmentation with generative models, and future directions and research opportunities.

Networking & bar
20:45 – 21:30

FAQ