Research Interests

My primary work is in the area of Deep Learning applied to Computer Vision, Natural Language Processing and Reinforcement Learning.

My main research interests in vision lie in:

image restoration tasks, such as super-resolution
tracking, alignment and pose estimation
key points localisation
(3D) scene understanding and reconstruction
cross-domain mapping
interplay between language and vision

My main research interests in NLP lie in:

neural machine translation (NMT)
multilingual NMT
robust NMT
embedding compression
sequence modeling

My main research interests in Deep RL lie in:

autonomous goal generation and intrinsic motivation
multitask learning and meta-learning
hierarchical reinforcement learning
interplay of RL with vision

In addition, I’m studying Graph Neural Networks.