Alert button
Picture for Matteo Pagliardini

Matteo Pagliardini

Alert button

DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging

Feb 04, 2024
Matteo Pagliardini, Amirkeivan Mohtashami, Francois Fleuret, Martin Jaggi

Viaarxiv icon

MEDITRON-70B: Scaling Medical Pretraining for Large Language Models

Nov 27, 2023
Zeming Chen, Alejandro Hernández Cano, Angelika Romanou, Antoine Bonnet, Kyle Matoba, Francesco Salvi, Matteo Pagliardini, Simin Fan, Andreas Köpf, Amirkeivan Mohtashami, Alexandre Sallinen, Alireza Sakhaeirad, Vinitra Swamy, Igor Krawczuk, Deniz Bayazit, Axel Marmet, Syrielle Montariol, Mary-Anne Hartley, Martin Jaggi, Antoine Bosselut

Viaarxiv icon

DoGE: Domain Reweighting with Generalization Estimation

Oct 23, 2023
Simin Fan, Matteo Pagliardini, Martin Jaggi

Viaarxiv icon

CoTFormer: More Tokens With Attention Make Up For Less Depth

Oct 16, 2023
Amirkeivan Mohtashami, Matteo Pagliardini, Martin Jaggi

Viaarxiv icon

Faster Causal Attention Over Large Sequences Through Sparse Flash Attention

Jun 01, 2023
Matteo Pagliardini, Daniele Paliotta, Martin Jaggi, François Fleuret

Figure 1 for Faster Causal Attention Over Large Sequences Through Sparse Flash Attention
Figure 2 for Faster Causal Attention Over Large Sequences Through Sparse Flash Attention
Figure 3 for Faster Causal Attention Over Large Sequences Through Sparse Flash Attention
Figure 4 for Faster Causal Attention Over Large Sequences Through Sparse Flash Attention
Viaarxiv icon

Revisiting the ACVI Method for Constrained Variational Inequalities

Oct 27, 2022
Tatjana Chavdarova, Matteo Pagliardini, Tong Yang, Michael I. Jordan

Figure 1 for Revisiting the ACVI Method for Constrained Variational Inequalities
Figure 2 for Revisiting the ACVI Method for Constrained Variational Inequalities
Figure 3 for Revisiting the ACVI Method for Constrained Variational Inequalities
Figure 4 for Revisiting the ACVI Method for Constrained Variational Inequalities
Viaarxiv icon

Improving Generalization via Uncertainty Driven Perturbations

Feb 28, 2022
Matteo Pagliardini, Gilberto Manunza, Martin Jaggi, Michael I. Jordan, Tatjana Chavdarova

Figure 1 for Improving Generalization via Uncertainty Driven Perturbations
Figure 2 for Improving Generalization via Uncertainty Driven Perturbations
Figure 3 for Improving Generalization via Uncertainty Driven Perturbations
Figure 4 for Improving Generalization via Uncertainty Driven Perturbations
Viaarxiv icon

Agree to Disagree: Diversity through Disagreement for Better Transferability

Feb 09, 2022
Matteo Pagliardini, Martin Jaggi, François Fleuret, Sai Praneeth Karimireddy

Figure 1 for Agree to Disagree: Diversity through Disagreement for Better Transferability
Figure 2 for Agree to Disagree: Diversity through Disagreement for Better Transferability
Figure 3 for Agree to Disagree: Diversity through Disagreement for Better Transferability
Figure 4 for Agree to Disagree: Diversity through Disagreement for Better Transferability
Viaarxiv icon

The Peril of Popular Deep Learning Uncertainty Estimation Methods

Dec 09, 2021
Yehao Liu, Matteo Pagliardini, Tatjana Chavdarova, Sebastian U. Stich

Figure 1 for The Peril of Popular Deep Learning Uncertainty Estimation Methods
Figure 2 for The Peril of Popular Deep Learning Uncertainty Estimation Methods
Figure 3 for The Peril of Popular Deep Learning Uncertainty Estimation Methods
Figure 4 for The Peril of Popular Deep Learning Uncertainty Estimation Methods
Viaarxiv icon