Accueil
Équipe
Publications
Open Source
Démos
Évènements
Blog
Carrières
Nous joindre
Français
Français
English
ServiceNow
ServiceNow recherche
Tags
Few-shot Learning
ServiceNow recherche
Few-shot Learning
A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches
Existing approaches for low-resource text summarization primarily employ large language models (LLMs) like GPT-3 or GPT-4 at inference …
Gaurav Sahu
,
Olga Vechtomova
,
Issam H. Laradji
North American Chapter of the Association for Computational Linguistics (NAACL), 2025.
PDF
Citation
Code
MixSumm: Topic-based Data Augmentation using LLMs for Low-resource Extractive Text Summarization
Low-resource extractive text summarization is a vital but heavily underexplored area of research. Prior literature either focuses on …
Issam H. Laradji
,
Gaurav Sahu
ArXiv, 2024.
PDF
Citation
PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillation
Data augmentation is a widely used technique to address the problem of text classification when there is a limited amount of training …
Gaurav Sahu
,
Olga Vechtomova
,
Dzmitry Bahdanau
,
Issam H. Laradji
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.
PDF
Citation
Code
Vidéo
MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting
Large pre-trained models have proved to be remarkable zero- and (prompt-based) few-shot learners in unimodal vision and language tasks. …
Oscar Manas
,
Pau Rodriguez
,
Saba Ahmadi
,
Aida Nematzadeh
,
Yash Goyal
,
Aishwarya Agrawal
European Chapter of the Association for Computational Linguistics (EACL), 2023.
PDF
Citation
Towards Learning to Imitate from a Single Video Demonstration
Agents that can learn to imitate given video observation – without direct access to state or action information are more …
Glen Berseth
,
Florian Golemo
,
Christopher Pal
Journal of Machine Learning Research (JMLR), 2023.
PDF
Citation
A Closer Look at Embedding Propagation for Manifold Smoothing
Supervised training of neural networks requires a large amount of manually annotated data and the resulting networks tend to be …
Diego Velazquez
,
Pau Rodriguez
,
Josep M. Gonfaus
,
F. Xavier Roca
,
Jordi Gonzalez
Journal of Machine Learning Research (JMLR), 2022.
PDF
Citation
Code
Overcoming challenges in leveraging GANs for few-shot data augmentation
In this paper, we explore the use of GAN-based few-shot data augmentation as a method to improve few-shot classification performance. …
Christopher Beckham
,
Issam H. Laradji
,
Pau Rodriguez
,
David Vazquez
,
Derek Nowrouzezahrai
,
Christopher Pal
Workshop at the Conference on Lifelong Learning Agents (CoLLAs), 2022.
PDF
Citation
A Survey of Self-Supervised and Few-Shot Object Detection
Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which …
Gabriel Huang
,
Issam H. Laradji
,
David Vazquez
,
Simon Lacoste-Julien
,
Pau Rodriguez
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2021.
PDF
Citation
Code
Synbols: Probing Learning Algorithms with Synthetic Datasets
Progress in the field of machine learning has been fueled by the introduction of benchmark datasets pushing the limits of existing …
Alexandre Lacoste
,
Pau Rodriguez
,
Frederic Branchaud
,
Parmida Atighhehchian
,
Massimo Caccia
,
Issam H. Laradji
,
Alexandre Drouin
,
Matt Craddock
,
Laurent Charlin
,
David Vazquez
Conference on Neural Information Processing Systems (NeurIPS), 2020.
PDF
Citation
Code
Embedding Propagation: Smoother Manifold for Few-Shot Classification
Few-shot classification is challenging because the data distribution of the training set can be widely different to the test set as …
Pau Rodriguez
,
Issam H. Laradji
,
Alexandre Drouin
,
Alexandre Lacoste
European Conference on Computer Vision (ECCV), 2020.
PDF
Citation
Code
»
Citation
×