Promoting robustness and compositionality in machine learning with insights from cognitive bottlenecks

Parameter, experience, and compute efficient deep reinforcement learning

Beyond top line metrics : understanding the trade-off between model size and generalization properties

Coordination in generative modeling, automatic differentiation and multi-agent learning

Building sample-efficient reinforcement learning

Probability flows in deep learning

Self-supervision for reinforcement learning

Beyond the status quo in deep reinforcement learning

Sequential decision modeling in uncertain conditions

Improving predictive behavior under distributional shift

AI alignment and generalization in deep learning

Controllable music performance synthesis via hierarchical modelling

Differentiable best response shaping

Stabilizing Q-Learning for continuous control

Emergence of language-like latents in deep neural networks

On discovering and learning structure under limited supervision

Syntactic inductive biases for deep learning methods

Advances in generative models for dynamic scenes

On iterated learning for task-oriented dialogue

Data-efficient reinforcement learning with self-predictive representations

Continuous coordination as a realistic scenario for lifelong learning

Towards deep unsupervised inverse graphics

On improving variational inference with low-variance multi-sample estimators

Estimation neuronale de l'information mutuelle.

Deep learning and reinforcement learning methods for grounded goal-oriented dialogue

Emerging communication between competitive agents

Representation learning in unsupervised domain translation

Towards learning sentence representation with self-supervision

Representation learning for dialogue systems

Advances in deep learning with limited supervision and computational resources

No Press Diplomacy

Latent variable language models

Generative models : a critical review

Exploring Attention Based Model for Captioning Images

Generative models for natural images

Deep Learning for Video Modelling

Sequence to sequence learning and its speech applications

Learning visual representations with neural networks for video captioning and image generation

Representation Learning for Visual Data

Towards deep semi supervised learning

Speech synthesis using recurrent neural networks

Influencing the Properties of Latent Spaces

Sequential modeling, generative recurrent neural networks, and their applications to audio

Deep learning of representations and its application to computer vision

Distributed conditional computation

Leveraging noisy side information for disentangling of factors of variation in a supervised setting

Promoting systematic generalization in vision-and-language foundation models

Canada Research Chair in Learning representations that generalize systematically

Nomination à titre de conseiller scientifique

Fellow, CCAI Chair, CIFAR program in Learning in Machines & Brains

Enhanced real-time object detection and space management for bus stop monitoring using fisheye camera technology from the SCiNe device of BusPas

Anomaly and Defect Detection in Orchards

Création d’images synthétiques de radar météorologique par télédétection pour la prévision immédiate des orages

Création d’images de super résolution à partir d’images multiplateforme pour des besoins en hydraulique

Design and develop an efficient offline computer vision system to detect site behavior at the bus stop using the SCiNe device of BusPas

Extending the Frontiers of Deep Generative Modelling

Mastering Multi-modal Decision-making with World-Models

Hierarchical Context Retrieval for LLM Question Answering

ML for Action Detection in Movies for Haptic Effects Generation

"Personal Assistant for Blind people”

High frequency measurement generation model from low frequency features››

Software infrastructure for Deep Learning

Generation model optimization

Physics-inspired Deep Generative Modeling and New Physics Search for High Energy Physics

Apogée Canada fonds d'excellence en recherche / Bourse d'excellence IVADO au doctorat Lluis E. Castrejon Subira

Unsupervised Learning of 3D Scenes from Images using a View-based Representation

Visual-haptic Representation for Zero-shot Learning

Support research related to the CIFAR program in Learning in Machines & Brains_Fellow

Fellow of the CIFAR LMB Program / CIFAR program Learning in Machine & Brains

Programme de stages - IVADO - Eugene Belilovsky /Towards Learning Language Based Navigation in Visually Rich 3-D Environments

Software infrastructure for Deep Learning

Unsupervised Learning of 3D Scenes from Images using a View-based Representation

Interative Grounded Language Understanding (IGLU)

CIFAR// Fellow // Research Support and Teaching Release // Learning in Machines & Brains

Apprentissage non-supervisé d'architectures profondes pour le changement d'expressions faciales

PROBABILISTIC MODELS FOR AUTOMATIC EQUIVARIANT FEATURE DISCOVERY

Highperformance computing environment to leverage deep learning technology for large biomedical and neuroimaging data

Deep Learning for Cognitive Computing

Interactive Grounded Language Understanding (IGLU)

RESEARCH ON SCALING UP DEEP LEARNING

DEVELOPPEMENT D'UN SYSTÈME ROBUSTE DE RECONNAISSANCE D'ACTIVITES HUMAINES UTILISANT DES FILMS ET LEUR TEXTE DESCRIPTIF

L'APPRENTISSAGE PROFOND DES IMAGES ET DU LANGAGE NATUREL

CIFAR//Fellow//Research Support

LARGE-SCALE DEEP LEARNING FOR CONTENT-BASED RECOMMENDATION SYSTEMS

ADIABATIC QUANTUM COMPUTING FOR DEEP LEARNING WITH BOLTZMANN MACHINES