Dublin Artificial Intelligence Applications Study Group cover photo

Dublin Artificial Intelligence Applications Study Group

Share

About us

A community-driven meetup to explore Artificial Intelligence from the ground up — theory, hands-on practice, and open discussion.

We study the technologies shaping modern AI: Large Language Models** like GPT, LLaMA, and Mistral — their architecture, fine-tuning, and prompt engineering — alongside Computer Vision, from object detection to diffusion-based generative models, and the Deep Learning foundations that make it all possible, including transformers, attention mechanisms, and neural network optimization.

We explore the frontier of AI Agents and Retrieval-Augmented Generation (RAG), where models become autonomous reasoners augmented with external tools and real-time knowledge. We also cover MLOps, the discipline of taking models from notebooks to production, and engage seriously with Ethics, Safety, and Alignment — because responsible AI starts with informed practitioners.

Every session is hands-on: we read landmark papers, work through notebooks, and build together. No prerequisites — just curiosity. Beginners and experienced practitioners alike are welcome.

📅 Join us and grow with us.
and open-source projects together
3. Get hands-on: notebooks, demos, mini-projects every session
4. Create a welcoming space for all levels — beginners and practitioners alike

📅 Join us — no prerequisites, just curiosity.

Upcoming events

1

Fine tuning LLM Vision Models
Sat, Apr 25 · 11:00 AM IST
The Grafton Hotel, 31/32 Stephen Street Lower Dublin 2 D02 WV05 Ireland, Dublin, IE
Vision Language Models (VLMs) such as LLaVA, Qwen-VL, Nemotron VL and GPT-4o have unlocked a new era in AI where language and sight converge into a single reasoning system. These models can describe images, answer visual questions, read documents, and interpret charts — but their true power emerges when you fine-tune them on domain-specific data, teaching them to see and reason about the visual world that matters to you.

In this hands-on session, we walk through the full fine-tuning pipeline for vision-language models. We begin by understanding how these architectures work — how a visual encoder like CLIP or SigLIP is coupled with a large language model through a projection layer, and how the interplay between image tokens and text tokens enables multimodal reasoning. We then move into the practical side: preparing image-text datasets, choosing the right fine-tuning strategy (full fine-tuning vs. LoRA vs. QLoRA), configuring training with frameworks like Hugging Face Transformers and PEFT, and evaluating results on real-world benchmarks.

We will also discuss when and why fine-tuning a VLM is the right approach compared to alternatives like prompt engineering or retrieval-augmented generation, and how to avoid common pitfalls such as catastrophic forgetting, overfitting on small visual datasets, and misaligned image-text pairs.

Bring your laptop, your curiosity, and — if you have one — a dataset you would like to try. By the end of the session you will have a clear, reproducible workflow for adapting any open-source vision-language model to a custom task.

**📅 Open to all levels — no prerequisites, just curiosity.**
1 attendee

Organizers

Members

1