Seminar: Local-metrics for multi-object tracking
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021
P.A.I.S.S. PRAIRIE Artificial Intelligence Summer School 2021
LeBenchmark: a reproducible framework for assessing self-supervised representation learning from speech
Continual adaptation of visual representations via domain randomization and meta-learning
Do multilingual neural machine translation models contain language pair specific attention heads?
Learning in a changing environment: memory strategies for streaming learning under distributional shifts.
Releasing first of a kind large-scale localization datasets in crowded indoor spaces
NAVER LABS releases world's biggest visual localization dataset of indoor spaces with over 130K images. Dataset built with NAVER LABS mapping robots M1X & COMET and available in unified data format kapture.
Risk-sensitive robot navigation
Using a novel algorithm we explore how effectively a single policy, learned by reinforcement learning, can modulate robot behaviour from risk-averse to risk-neutral, so that robots can safely navigate everyday environments like homes and shops.
Debiasing large pretrained language models using distributional control
A novel framework for controlled NLG called 'Generation with Distributional Control', achieves great generality on the types of constraints that can be imposed and has a large potential to remedy the problem of bias in language models.
GLOBAL AI R&D BELT
ACADEMIA – EU/GOVT – ENTREPRENEURS
Our partnerships range from long-term fundamental research to investment in products and services.