works on

From the 2 of 35 linked papers with an AI index.

activity
20242026
collaborators
Showing 2024Show all

8 papers · 1 filter

cs.LG2024

Non-Uniform Parameter-Wise Model Merging

Albert Manuel Orozco Camacho, Stefan Horoi, Guy Wolf +1

Combining multiple machine learning models has long been a technique for enhancing performance, particularly in distributed settings. Traditional approaches, such as model ensemble…

cs.LG2024

Not Only the Last-Layer Features for Spurious Correlations: All Layer Deep Feature Reweighting

Humza Wajid Hameed, Geraldin Nanfack, Eugene Belilovsky

Spurious correlations are a major source of errors for machine learning models, in particular when aiming for group-level fairness. It has been recently shown that a powerful appro…

cs.LG2024

Simple and Scalable Strategies to Continually Pre-train Large Language Models

Adam Ibrahim, Benjamin Thérien, Kshitij Gupta +5

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start the process over again once new data becomes available. A much more efficient solution i…

cs.LG2024

Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks

MohammadReza Davari, Eugene Belilovsky

The rapid development of AI systems has been greatly influenced by the emergence of foundation models. A common approach for targeted problems involves fine-tuning these pre-traine…

cs.LG2024

Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis

Stefan Horoi, Albert Manuel Orozco Camacho, Eugene Belilovsky +1

Combining the predictions of multiple trained models through ensembling is generally a good way to improve accuracy by leveraging the different learned features of the models, howe…

cs.CV2024

From Feature Visualization to Visual Circuits: Effect of Adversarial Model Manipulation

Geraldin Nanfack, Michael Eickenberg, Eugene Belilovsky

Understanding the inner working functionality of large-scale deep neural networks is challenging yet crucial in several high-stakes applications. Mechanistic inter- pretability is…