58 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Département d'InformatiqueFR8 papers
- Willow Biosciences (Canada)CA6 papers
- École Normale Supérieure - PSLFR5 papers
- Campo Arqueologico de MertolaPT3 papers
- Laboratoire d'Analyse et d'Architecture des SystèmesFR3 papers
- Courant Institute of Mathematical SciencesUS2 papers
- Getty Research InstituteUS2 papers
- Institut national de recherche en sciences et technologies du numériqueFR2 papers
- Laboratoire d'Informatique, de Robotique et de Microélectronique de MontpellierFR2 papers
- Meta (United States)US2 papers
- Carnegie Mellon UniversityUS1 paper
- Czech Technical University in PragueCZ1 paper
3 papers · 1 filter
Dual Perspectives on Non-Contrastive Self-Supervised Learning
Jean Ponce, Basile Terver, Martial Hebert +1
The {\em stop gradient} and {\em exponential moving average} iterative procedures are commonly used in non-contrastive approaches to self-supervised learning to avoid representatio…
On the duality between contrastive and non-contrastive self-supervised learning
Quentin Garrido, Yubei Chen, Adrien Bardes +2
Recent approaches in self-supervised learning of image representations can be categorized into different families of methods and, in particular, can be divided into contrastive and…
Residual Reinforcement Learning from Demonstrations
Minttu Alakuijala, Gabriel Dulac-Arnold, Julien Mairal +2
Residual reinforcement learning (RL) has been proposed as a way to solve challenging robotic tasks by adapting control actions from a conventional feedback controller to maximize a…