3 papers
cs.LG2025
Layer by Layer: Uncovering Hidden Representations in Language Models
Oscar Skean, Md Rifat Arefin, Dan Zhao +4
From extracting features to generating text, the outputs of large language models (LLMs) typically rely on the final layers, following the conventional wisdom that earlier layers c…
cs.LG2024
Does Representation Matter? Exploring Intermediate Layers in Large Language Models
Oscar Skean, Md Rifat Arefin, Yann LeCun +1
Understanding what defines a good representation in large language models (LLMs) is fundamental to both theoretical understanding and practical applications. In this paper, we inve…
cs.LG2024
FroSSL: Frobenius Norm Minimization for Efficient Multiview Self-Supervised Learning
Oscar Skean, Aayush Dhakal, Nathan Jacobs +1
Self-supervised learning (SSL) is a popular paradigm for representation learning. Recent multiview methods can be classified as sample-contrastive, dimension-contrastive, or asymme…