July 15 - Brussels AI, ML and Computer Vision Meetup

Join us on July 15 for the Brussels AI, ML and Computer Vision Meetup.

Pre-registration is mandatory to clear building security. Click to sign up.

* Time: 5:30-8:30 PM
* Location: Commons Hub - Rue de la Madeleine 51, Brussels

Talks will include...

Enhancing Data Quality with Zero-Shot Detections

Check out the winning solution of the Wake Vision Challenge 2025 as we showcase how smart and efficient data curation and exploration, can generate good model performance from small subsets.

About the Speaker

Kais Bedioui is a Tunisian Computer Vision Engineer based in Belgium. He posesses a track record of working on Edge AI projects across several industries. In 2020 he started his Computer Vision and AI journey pursuing his master thesis at BMW where he integrated vision solutions into logistics robots.

The Computer Vision Ecosystem at Hugging Face

Niels will describe all things computer vision at Hugging Face, from models you can use out-of-the-box, models you can use to fine-tune on your specific data, as well as ongoing and upcoming trends

About the Speaker

Niels works as a Machine Learning Engineer for 2 companies, ML6 and Hugging Face. ML6 is a Belgian AI consulting company implementing (Gen)AI projects for large enterprises. Hugging Face is considered the home of open and collaborative machine learning, making sure anyone can benefit from state-of-the-art AI technology.

Adding Temporal Data to Object Detection Models

Object detection models are used for a lot of variety of tasks. However they are limited in seeing only the current image making it hard to detect objects in non ideal condition like: poor lighting, motion blur, etc. In this talk we will look at adding temporal data into existing object detection models without adding a lot of overhead. And how Fiftyone makes it easy to compare the model trained on temporal data vs static image data

About the Speaker

Joy is a machine learning engineer building a proactive intrusion detection system.

Visual Agents: What it takes to build an agent that can navigate GUIs like humans

We’ll examine conceptual frameworks, potential applications, and future directions of technologies that can “see” and “act” with increasing independence. The discussion will touch on both current limitations and promising horizons in this evolving field.

About the Speaker

Harpreet Sahota is a hacker-in-residence and machine learning engineer with a passion for deep learning and generative AI. He’s got a deep interest in RAG, Agents, and Multimodal AI.