171 citations · 246 across the 15 of their papers we have counts for
7 papers · 1 filter
AI Consciousness and Existential Risk
Rufin VanRullen
In AI, the existential risk denotes the hypothetical threat posed by an artificial system that would possess both the capability and the objective, either directly or indirectly, t…
Multimodal Dreaming: A Global Workspace Approach to World Model-Based Reinforcement Learning
Léopold Maytié, Roland Bertin Johannet, Rufin VanRullen
Humans leverage rich internal models of the world to reason about the future, imagine counterfactuals, and adapt flexibly to new situations. In Reinforcement Learning (RL), world m…
Tracking objects that change in appearance with phase synchrony
Sabine Muzellec, Drew Linsley, Alekh K. Ashok +4
Objects we encounter often change appearance as we interact with them. Changes in illumination (shadows), object pose, or the movement of non-rigid objects can drastically alter av…
Zero-shot cross-modal transfer of Reinforcement Learning policies through a Global Workspace
Léopold Maytié, Benjamin Devillers, Alexandre Arnold +1
Humans perceive the world through multiple senses, enabling them to create a comprehensive representation of their surroundings and to generalize information across domains. For in…
Saliency strikes back: How filtering out high frequencies improves white-box explanations
Sabine Muzellec, Thomas Fel, Victor Boutin +3
Attribution methods correspond to a class of explainability methods (XAI) that aim to assess how individual inputs contribute to a model's decision-making process. We have identifi…
Semi-supervised Multimodal Representation Learning through a Global Workspace
Benjamin Devillers, Léopold Maytié, Rufin VanRullen
Recent deep learning models can efficiently combine inputs from different modalities (e.g., images and text) and learn to align their latent representations, or to translate signal…
Does language help generalization in vision models?
Benjamin Devillers, Bhavin Choksi, Romain Bielawski +1
Vision models trained on multimodal datasets can benefit from the wide availability of large image-caption datasets. A recent model (CLIP) was found to generalize well in zero-shot…