ML Pub Club #23: GenAI Tradeoff - Train Small In-House or Prompt Large LLMs?

Small models, in-house training or massive LLMs at your fingertips? Which path gives you the best accuracy, speed, cost efficiency, and real-world reliability? 🤔 

​Our ML Pub Club returns and we are kicking things off with Patrik Mesec, Data Science Team Lead at Aircash, as he shares the story of their tiny vision-language model, the engine behind their automated identity verification system. 🛠️ 

From designing a model small enough to run efficiently in-house, to learning how to detect hallucinations and when to rely on large LLMs, Patrik will take you through the real-world challenges and decisions that shaped their AI journey, the pros and cons of in-house training vs. prompting large LLMs, how to compress models without losing performance, techniques to catch and prevent AI hallucinations! 🎯

​🗓️ Tuesday I October 7th, 2025

🕖 6PM

📍 CroAI HQ's (Zavrtnica 17, 4th floor)