Picture for Yann Dauphin

Yann Dauphin

Universite de Montreal

Avoiding spurious sharpness minimization broadens applicability of SAM

Add code
Feb 04, 2025
Viaarxiv icon

Towards Optimal Adapter Placement for Efficient Transfer Learning

Add code
Oct 21, 2024
Figure 1 for Towards Optimal Adapter Placement for Efficient Transfer Learning
Figure 2 for Towards Optimal Adapter Placement for Efficient Transfer Learning
Figure 3 for Towards Optimal Adapter Placement for Efficient Transfer Learning
Figure 4 for Towards Optimal Adapter Placement for Efficient Transfer Learning
Viaarxiv icon

A density estimation perspective on learning from pairwise human preferences

Add code
Nov 30, 2023
Figure 1 for A density estimation perspective on learning from pairwise human preferences
Figure 2 for A density estimation perspective on learning from pairwise human preferences
Figure 3 for A density estimation perspective on learning from pairwise human preferences
Figure 4 for A density estimation perspective on learning from pairwise human preferences
Viaarxiv icon

Tied-Augment: Controlling Representation Similarity Improves Data Augmentation

Add code
May 22, 2023
Viaarxiv icon

JaxPruner: A concise library for sparsity research

Add code
May 02, 2023
Figure 1 for JaxPruner: A concise library for sparsity research
Figure 2 for JaxPruner: A concise library for sparsity research
Figure 3 for JaxPruner: A concise library for sparsity research
Viaarxiv icon

Robustmix: Improving Robustness by Regularizing the Frequency Bias of Deep Nets

Add code
Apr 06, 2023
Viaarxiv icon

No One Representation to Rule Them All: Overlapping Features of Training Methods

Add code
Oct 26, 2021
Figure 1 for No One Representation to Rule Them All: Overlapping Features of Training Methods
Figure 2 for No One Representation to Rule Them All: Overlapping Features of Training Methods
Figure 3 for No One Representation to Rule Them All: Overlapping Features of Training Methods
Figure 4 for No One Representation to Rule Them All: Overlapping Features of Training Methods
Viaarxiv icon

Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral

Add code
Aug 25, 2021
Figure 1 for Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral
Figure 2 for Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral
Figure 3 for Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral
Figure 4 for Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral
Viaarxiv icon

Continental-Scale Building Detection from High Resolution Satellite Imagery

Add code
Jul 29, 2021
Figure 1 for Continental-Scale Building Detection from High Resolution Satellite Imagery
Figure 2 for Continental-Scale Building Detection from High Resolution Satellite Imagery
Figure 3 for Continental-Scale Building Detection from High Resolution Satellite Imagery
Figure 4 for Continental-Scale Building Detection from High Resolution Satellite Imagery
Viaarxiv icon

Temperature check: theory and practice for training models with softmax-cross-entropy losses

Add code
Oct 14, 2020
Figure 1 for Temperature check: theory and practice for training models with softmax-cross-entropy losses
Figure 2 for Temperature check: theory and practice for training models with softmax-cross-entropy losses
Figure 3 for Temperature check: theory and practice for training models with softmax-cross-entropy losses
Figure 4 for Temperature check: theory and practice for training models with softmax-cross-entropy losses
Viaarxiv icon