Conference Agenda

Brief Description and Outline:

Foundation models can be adapted in many ways, but it’s often unclear how these approaches differ beyond their descriptions. In this interactive workshop, we start from a fixed pretrained check-point and walk through several prominent adaptation strategies (linear probing, LoRA, prompt-based methods, and related techniques). Using a shared base experiment, participants will run hands-on notebooks that visualize parameter updates, representational shifts, and performance changes across methods.

-

Goals:

Build practical intuition for major adaptation strategies

-

Presenters Experience:

Dasha Trofimova is a ML engineer at DKFZ with over 10 years of experience applying DL methods to biomedical and scientific problems. I did the workshop last year at HAICON and have teaching experience.

-

Target Audience:

researchers with data analytics experience

-

Keywords:

Model Adaptation, Parameter-Efficient Fine-Tuning, Foundation Model