ProfessorsProfessors of McGill UniversityLucas Caccia

Lucas Caccia

McGill University

H-index: 10

North America-Canada

About Lucas Caccia

Lucas Caccia, With an exceptional h-index of 10 and a recent h-index of 10 (since 2020), a distinguished researcher at McGill University, specializes in the field of Deep Learning, Continual Learning, Natural Language Processing.

His recent articles reflect a diverse array of research interests and contributions to the field:

Generative Modeling of Individual Behavior at Scale

Guiding language model reasoning with planning tokens

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

Multi-Head Adapter Routing for Cross-Task Generalization

A Case Study of Instruction Tuning with Mixture of Parameter-Efficient Experts

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

Building a subspace of policies for scalable continual learning

On Anytime Learning at Macroscale

Lucas Caccia Information

University	McGill University
Position	MILA;
Citations(all)	1301
Citations(since 2020)	1295
Cited By	214
hIndex(all)	10
hIndex(since 2020)	10
i10Index(all)	11
i10Index(since 2020)	11
Email	Access Email
University Profile Page	McGill University
Google Scholar	View Google Scholar Profile

Lucas Caccia Skills & Research Interests

Deep Learning

Continual Learning

Natural Language Processing

Top articles of Lucas Caccia

Title	Journal	Author(s)	Publication Date
Generative Modeling of Individual Behavior at Scale		Nabil Omi Lucas Caccia Siddhartha Sen Anurag Sarkar Jordan T Ash	2023/10/13
Guiding language model reasoning with planning tokens	arXiv preprint arXiv:2310.05707	Xinyi Wang Lucas Caccia Oleksiy Ostapenko Xingdi Yuan Alessandro Sordoni	2023/10/9
Guiding The Last Layer in Federated Learning with Pre-Trained Models	NeurIPS 2023	Gwen Legate Nicolas Bernier Lucas Caccia Edouard Oyallon Eugene Belilovsky	2023/6/6
Multi-Head Adapter Routing for Cross-Task Generalization	NeurIPS 2023	Lucas Page-Caccia Edoardo Maria Ponti Zhan Su Matheus Pereira Nicolas Le Roux ...	2023/2/13
A Case Study of Instruction Tuning with Mixture of Parameter-Efficient Experts		Oleksiy Ostapenko Lucas Caccia Zhan Su Nicolas Le Roux Laurent Charlin ...	2023/11/26
Re-Weighted Softmax Cross-Entropy to Control Forgetting in Federated Learning	Collas 2023	Gwen Legate Lucas Caccia Eugene Belilovsky	2023/4/11
Building a subspace of policies for scalable continual learning	ICLR 2023	Jean-Baptiste Gaya Thang Doan Lucas Caccia Laure Soulier Ludovic Denoyer ...	2022/11/18
On Anytime Learning at Macroscale	CoLLAs 2022	Lucas Caccia Jing Xu Myle Ott Marc'Aurelio Ranzato Ludovic Denoyer	2021/6/17
SPeCiaL: Self-Supervised Pretraining for Continual Learning	IJCAI 2021, Workshop on Continual Semi-Supervised Learning, Best Paper Award	Lucas Caccia Joelle Pineau	2021/6/16
Decoupled greedy learning of cnns for synchronous and asynchronous distributed learning	arXiv preprint arXiv:2106.06401	Eugene Belilovsky Louis Leconte Lucas Caccia Michael Eickenberg Edouard Oyallon	2021/6/11
New Insights on Reducing Abrupt Representation Change in Online Continual Learning	ICLR 2022	Lucas Caccia Rahaf Aljundi Nader Asadi Tinne Tuytelaars Joelle Pineau ...	2022/3/8
Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning	NeurIPS 2020	Massimo Caccia Pau Rodriguez Oleksiy Ostapenko Fabrice Normandin Min Lin ...	2020/3/12