Alert button
Picture for Lucas Caccia

Lucas Caccia

Alert button

MILA

Guiding Language Model Reasoning with Planning Tokens

Oct 09, 2023
Xinyi Wang, Lucas Caccia, Oleksiy Ostapenko, Xingdi Yuan, Alessandro Sordoni

Figure 1 for Guiding Language Model Reasoning with Planning Tokens
Figure 2 for Guiding Language Model Reasoning with Planning Tokens
Figure 3 for Guiding Language Model Reasoning with Planning Tokens
Figure 4 for Guiding Language Model Reasoning with Planning Tokens
Viaarxiv icon

Guiding The Last Layer in Federated Learning with Pre-Trained Models

Jun 06, 2023
Gwen Legate, Nicolas Bernier, Lucas Caccia, Edouard Oyallon, Eugene Belilovsky

Figure 1 for Guiding The Last Layer in Federated Learning with Pre-Trained Models
Figure 2 for Guiding The Last Layer in Federated Learning with Pre-Trained Models
Figure 3 for Guiding The Last Layer in Federated Learning with Pre-Trained Models
Figure 4 for Guiding The Last Layer in Federated Learning with Pre-Trained Models
Viaarxiv icon

Re-Weighted Softmax Cross-Entropy to Control Forgetting in Federated Learning

Apr 11, 2023
Gwen Legate, Lucas Caccia, Eugene Belilovsky

Figure 1 for Re-Weighted Softmax Cross-Entropy to Control Forgetting in Federated Learning
Figure 2 for Re-Weighted Softmax Cross-Entropy to Control Forgetting in Federated Learning
Figure 3 for Re-Weighted Softmax Cross-Entropy to Control Forgetting in Federated Learning
Figure 4 for Re-Weighted Softmax Cross-Entropy to Control Forgetting in Federated Learning
Viaarxiv icon

Building a Subspace of Policies for Scalable Continual Learning

Nov 18, 2022
Jean-Baptiste Gaya, Thang Doan, Lucas Caccia, Laure Soulier, Ludovic Denoyer, Roberta Raileanu

Figure 1 for Building a Subspace of Policies for Scalable Continual Learning
Figure 2 for Building a Subspace of Policies for Scalable Continual Learning
Figure 3 for Building a Subspace of Policies for Scalable Continual Learning
Figure 4 for Building a Subspace of Policies for Scalable Continual Learning
Viaarxiv icon

Multi-Head Adapter Routing for Data-Efficient Fine-Tuning

Nov 07, 2022
Lucas Caccia, Edoardo Ponti, Lucas Liu, Matheus Pereira, Nicolas Le Roux, Alessandro Sordoni

Figure 1 for Multi-Head Adapter Routing for Data-Efficient Fine-Tuning
Figure 2 for Multi-Head Adapter Routing for Data-Efficient Fine-Tuning
Figure 3 for Multi-Head Adapter Routing for Data-Efficient Fine-Tuning
Figure 4 for Multi-Head Adapter Routing for Data-Efficient Fine-Tuning
Viaarxiv icon

New Insights on Reducing Abrupt Representation Change in Online Continual Learning

Mar 08, 2022
Lucas Caccia, Rahaf Aljundi, Nader Asadi, Tinne Tuytelaars, Joelle Pineau, Eugene Belilovsky

Figure 1 for New Insights on Reducing Abrupt Representation Change in Online Continual Learning
Figure 2 for New Insights on Reducing Abrupt Representation Change in Online Continual Learning
Figure 3 for New Insights on Reducing Abrupt Representation Change in Online Continual Learning
Figure 4 for New Insights on Reducing Abrupt Representation Change in Online Continual Learning
Viaarxiv icon

On Anytime Learning at Macroscale

Jun 17, 2021
Lucas Caccia, Jing Xu, Myle Ott, Marc'Aurelio Ranzato, Ludovic Denoyer

Figure 1 for On Anytime Learning at Macroscale
Figure 2 for On Anytime Learning at Macroscale
Figure 3 for On Anytime Learning at Macroscale
Figure 4 for On Anytime Learning at Macroscale
Viaarxiv icon

SPeCiaL: Self-Supervised Pretraining for Continual Learning

Jun 16, 2021
Lucas Caccia, Joelle Pineau

Figure 1 for SPeCiaL: Self-Supervised Pretraining for Continual Learning
Figure 2 for SPeCiaL: Self-Supervised Pretraining for Continual Learning
Figure 3 for SPeCiaL: Self-Supervised Pretraining for Continual Learning
Figure 4 for SPeCiaL: Self-Supervised Pretraining for Continual Learning
Viaarxiv icon

Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous Distributed Learning

Jun 11, 2021
Eugene Belilovsky, Louis Leconte, Lucas Caccia, Michael Eickenberg, Edouard Oyallon

Figure 1 for Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous Distributed Learning
Figure 2 for Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous Distributed Learning
Figure 3 for Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous Distributed Learning
Figure 4 for Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous Distributed Learning
Viaarxiv icon

Reducing Representation Drift in Online Continual Learning

Apr 11, 2021
Lucas Caccia, Rahaf Aljundi, Tinne Tuytelaars, Joelle Pineau, Eugene Belilovsky

Figure 1 for Reducing Representation Drift in Online Continual Learning
Figure 2 for Reducing Representation Drift in Online Continual Learning
Figure 3 for Reducing Representation Drift in Online Continual Learning
Figure 4 for Reducing Representation Drift in Online Continual Learning
Viaarxiv icon