View Proposal

Proposer
Alessandro Suglia
Title
Interpreting pixel-based large language models
Goal
To study and implement interpretability techniques for pixel-based language models
Description
Resources
https://arxiv.org/abs/2410.12011 https://arxiv.org/abs/2401.03321
Background
Experience with deep learning techniques with a special focus on Transformer-based models
Url
Difficulty Level
Moderate
Ethical Approval
None
Number Of Students
1
Supervisor
Alessandro Suglia
Keywords
deep learning; large language models; generative ai
Degrees
Master of Science in Artificial Intelligence
Master of Science in Data Science
Master of Science in Human Robot Interaction
Master of Science in Robotics
Back to List