KInIT Natural Language Processing Summer School 2025

The next edition of KInIT’s Natural Language Processing School will take place from September 3rd to September 5th 2025. The main goal of the event is to provide participants with an introduction to natural language processing – the area that currently drives much of the progress in AI. We are going to combine theory with hands-on sessions, starting with the basics and building up to more advanced topics, including where the state of the art is headed.

The event will take place at the Kempelen Institute for Intelligent Technologies (KInIT) in Bratislava, and it will be conducted by experts from KInIT and from our partner institutions. The event is free of charge. We are planning to welcome mostly university students (any year of study), but we are also open to considering applications from smart high school students. The capacity of the venue is limited, and participants will be selected based on their application forms.

Kempelen Institute of Intelligent Technologies (KInIT) is an independent, non-profit institute dedicated to intelligent technology research. On our mission of interconnecting academia and industry, we bring together and nurture experts in artificial intelligence and other areas of computer science, with connections to other disciplines.

When?

  • 3rd – 5th September 2025

Daily programme:

  • 8:30 – 9:00: [first day] Welcome breakfast
  • 9:00 – 10:35: first slot (1h 35 min)
  • 10:35 – 10:50 coffee break (15 min)
  • 10:50 – 12:30 second slot (1h 40 min)
  • 12:30 – 13:15 lunch
  • 13:15 – 14:50 (1h 35 min): third slot
  • 14:50 – 15:05 (15 min) coffee break
  • 15:05 – 16:40 (1h 35 min) fourth slot

Topics covered

(A more detailed breakdown of days and slots will be shared soon.)

  • Introduction to the basic machine learning concepts and deep learning;
  • Introduction to large language models;
  • LLMs as a game changer in AI + current limitations of LLMs;
  • Evaluation of large language models (with authors of skLEP, Slovakia’s first benchmark);
  • Parameter-efficient fine-tuning methods (i.e. fine-tuning models with lower memory requirements, lower capacity, etc.);
  • LLM pipelines (including retrieval augmented generation = RAG and LLM agents);
  • Vision-language models (and how we probe for what they really do and do not understand);
  • 1-2 more topics TBD;

KInIT team you’ll meet

Michal Gregor
Researcher
Martin Tamajka
Research Engineer
Marián Šimko
Lead and Researcher
Kamil Burda
Researcher
Eduard Mittaš
Research Engineer

Registration

Register here; deadline: August 10th 2025

Partners

KInIT Natural Language Processing Winter School is sponsored by Nadačný fond Telekom pri Nadácii Pontis.