3.4k citations · 4.7k across the 28 of their papers we have counts for
6 papers · 1 filter
The Edge of Orthogonality: A Simple View of What Makes BYOL Tick
Pierre H. Richemond, Allison Tam, Yunhao Tang +3
Self-predictive unsupervised learning methods such as BYOL or SimSiam have shown impressive results, and counter-intuitively, do not collapse to trivial representations. In this wo…
Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness
Mathieu Seurin, Florian Strub, Philippe Preux +1
Sparse rewards are double-edged training signals in reinforcement learning: easy to design but hard to optimize. Intrinsic motivation guidances have thus been developed toward alle…
The Monte Carlo Transformer: a stochastic self-attention model for sequence prediction
Alice Martin, Charles Ollion, Florian Strub +2
This paper introduces the Sequential Monte Carlo Transformer, an original approach that naturally captures the observations distribution in a transformer architecture. The keys, qu…
Bootstrap your own latent: A new approach to self-supervised Learning
Jean-Bastien Grill, Florian Strub, Florent Altché +11
We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target…
HIGhER : Improving instruction following with Hindsight Generation for Experience Replay
Geoffrey Cideron, Mathieu Seurin, Florian Strub +1
Language creates a compact representation of the world and allows the description of unlimited situations and objectives through compositionality. While these characterizations may…
Hybrid Recommender System based on Autoencoders
Florian Strub, Romaric Gaudel, Jérémie Mary
A standard model for Recommender Systems is the Matrix Completion setting: given partially known matrix of ratings given by users (rows) to items (columns), infer the unknown ratin…