activity
20242026
collaborators

5 papers

cs.LG2026

Can Model Merging Improve Aggregation in DiLoCo?

Stefan Horoi, Benjamin Thérien, Guy Wolf +1

Model merging techniques, which aggregate independently finetuned models into one to combine their capabilities, have become a topic of significant interest in recent years, with a…

cs.LG2026

From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging

Stefan Horoi, Guy Wolf, Eugene Belilovsky +1

Modern deep learning is increasingly characterized by the use of open-weight foundation models that can be fine-tuned on specialized datasets. This has led to a proliferation of ex…

cs.LG2025

Test Time Adaptation Using Adaptive Quantile Recalibration

Paria Mehrbod, Pedro Vianna, Geraldin Nanfack +2

Domain adaptation is a key strategy for enhancing the generalizability of deep learning models in real-world scenarios, where test distributions often diverge significantly from th…

cs.LG2025

AdaFisher: Adaptive Second Order Optimization via Fisher Information

Damien Martins Gomes, Yanlei Zhang, Eugene Belilovsky +2

First-order optimization methods are currently the mainstream in training deep neural networks (DNNs). Optimizers like Adam incorporate limited curvature information by employing t…

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…