2 papers
cs.CL2025
Semantic Convergence: Investigating Shared Representations Across Scaled LLMs
Daniel Son, Sanjana Rathore, Andrew Rufail +6
We investigate feature universality in Gemma-2 language models (Gemma-2-2B and Gemma-2-9B), asking whether models with a four-fold difference in scale still converge on comparable…
cs.CV2023
Learning Nuclei Representations with Masked Image Modelling
Piotr Wójcik, Hussein Naji, Adrian Simon +2
Masked image modelling (MIM) is a powerful self-supervised representation learning paradigm, whose potential has not been widely demonstrated in medical image analysis. In this wor…