About
People
Publications
Open Source
Demos
Events
Blog
Careers
Contact
English
English
Français
ServiceNow
ServiceNow Research
Tags
Efficient Learning
ServiceNow Research
Efficient Learning
Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts
Merging parameter-efficient task experts has recently gained growing attention as a way to build modular architectures that can be …
Samin Yeasar Arnob
,
Oleksiy Ostapenko
,
Alessandro Sordoni
,
Lucas Caccia
Conference on Language Modeling (COLM), 2025.
PDF
Cite
Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts
Merging parameter-efficient task experts has recently gained growing attention as a way to build modular architectures that can be …
Samin Yeasar Arnob
,
Zhan Su
,
Minseon Kim
,
Oleksiy Ostapenko
,
Doina Precup
,
Lucas Caccia
,
Alessandro Sordoni
Workshop at the International Conference of Learning Representation (ICLR), 2025.
PDF
Cite
Unifying Autoregressive and Diffusion-Based Sequence Generation
We take significant steps toward unifying autoregressive and diffusion-based sequence generation by extending the SEDD discrete …
Nima Fathi
,
Torsten Scholak
,
Pierre-André Noël
Workshop at the International Conference of Learning Representation (ICLR), 2025.
PDF
Cite
Automatic Data Augmentation Learning using Bilevel Optimization for Histopathological Images
One of the main challenges faced when training a deep learning based model to classify histopathological images is the color and shape …
Saypraseuth Mounsaveng
,
Issam H. Laradji
,
David Vazquez
,
Marco Pedersoli
,
Ismail Ben Ayed
ArXiv, 2024.
PDF
Cite
Code
Workflow discovery in low data regimes
Text-based dialogues are now widely used to solve real-world problems. In cases where solution strategies are already known, they can …
Amine El Hattami
,
Issam H. Laradji
,
Stefania Raimondo
,
David Vazquez
,
Pau Rodriguez
,
Christopher Pal
Workshop at the International Conference on Machine Learning (ICML), 2023.
PDF
Cite
Breadth-First Pipeline Parallelism
We introduce Breadth-First Pipeline Parallelism, a novel training schedule which optimizes the combination of pipeline and data …
Joel Lamy Poirier
Conference on Machine Learning and Systems (MLSYS), 2023.
PDF
Cite
Unsupervised Model-based Pre-training for Data-efficient Reinforcement Learning from Pixels
Reinforcement learning (RL) aims at autonomously performing complex tasks. To this end, a reward signal is used to steer the learning …
Sai Rajeswar Mudumba
,
Pietro Mazzaglia
,
Tim Verbelen
,
Alexandre Piche
,
Aaron Courville
,
Alexandre Lacoste
Workshop at the International Conference on Machine Learning (ICML), 2022.
PDF
Cite
Code
Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data
Multi-Task Learning (MTL) networks have emerged as a promising method for transferring learned knowledge across different tasks. …
Jonathan Pilault
,
Amine El Hattami
,
Christopher Pal
International Conference on Learning Representations (ICLR), 2021.
PDF
Cite
Code
Cite
×