Blog | NAVER LABS Europe
27 February 2021

Approaches to managing risk and high-level control in intelligent agents

Agents are becoming more artificially intelligent but a number of problems must be solved before we can unleash them into our physical world (i.e. robots) and trust them in our digital one.
18 December 2020
Blog Colbert Image

A white box analysis of ColBERT

By dissecting the matching process of the recent ColBERT model, we make a step towards unveiling the ranking properties of BERT-based ranking models and show that ColBERT (implicitly) learns a notion of term importance that correlates with IDF.
15 December 2020
RunAgead Blog Image

Running into the unknown with RunAhead

Running into the unknown with RunAhead: finding pleasant running tours and intuitively navigating through them. The use of combinatorial optimization and UX design, together with head-tracking technology, provides a non-intrusive way of helping runners to discover new itineraries.
9 December 2020
SuperLoss blog image

SuperLoss: Robust curriculum learning helps machines to learn like humans

A novel framework which uses individual sample losses as error measures to determine the relative difficulty of samples in a dataset. Can be plugged on top of existing neural network models to implement curriculum learning for any task, even with noisy datasets.
8 December 2020
Blog Image Constrastive Learning

Improving self-supervised representation learning by synthesizing challenging negatives

How harder negatives facilitate better and faster contrastive self-supervised learning and ways of synthesizing harder negative features on-the-fly.
7 December 2020
Julien Perez podcast

Robot learning workshop at NeurIPS2020 – podcast with Julien Perez

Podcast and transcript on 3rd Robot Learning Workshop at NeurIPS 2020 with Julien Perez, group lead machine learning and optimization at NAVER LABS Europe and co-organiser of the workshop.
24 November 2020
web image search blog image

Web image search gets better with graph neural networks

A new approach to image search uses images returned by traditional search methods as nodes in a graph neural network through which similarity signals are propagated, achieving improved ranking in cross-modal retrieval.
5 November 2020

A solution for greater algorithmic fairness in digital ranking systems

A new greedy, brute-force solution improves fairness in ranking and encompasses realistic scenarios with multiple, unknown protected groups.
16 October 2020

Flow: enabling non-technical people to create and maintain applications

By incorporating a set of reusable constructs that enable advanced functionality, Flow makes platform-agnostic application modelling, creation, distribution and maintenance easy.
24 August 2020
Learning Visual Representations

Learning visual representations with caption annotations

How mid-size sets of captioned images can rival with large-scale labelled image sets to learn generic representations
21 August 2020

DOPE: distillation of part experts for whole-body 3D pose estimation in the wild

A novel efficient model for whole-body 3D pose estimation (including bodies, hands and faces), that is trained by mimicking the output of hand-, body- and face-pose experts.
4 August 2020
force blog image

FORCE enables extreme pruning of artificial neural networks at initialization

A new method called FORCE achieves extreme sparsity in artificial neural networks by progressively removing up to 99.9% of parameters at initialization, making it a promising candidate for training networks on edge devices (like drones or smartphones).