NAVER LABS Europe Homepage
A new family of approaches to few-shot imitation
A NEW FAMILY OF APPROACHES
TO FEW-SHOT IMITATION:

DEMONSTRATION-CONDITIONED REINFORCEMENT LEARNING
SPLADE
SPLADE – A SPARSE BI-ENCODER BERT-BASED MODEL ACHIEVES EFFECTIVE AND EFFICIENT FIRST-STAGE RANKING
GDC
A DISTRIBUTIONAL
APPROACH TO
CONTROLLED TEXT
GENERATION
CONTINUAL LEARNING
CONTINUAL LEARNING OF VISUAL REPRESENTATIONS WITHOUT CATASTROPHIC FORGETTING
About Us
ACL 2021

ACL-IJCNLP 2021

1st - 6th August 2021, online. 2 papers on NMT and workshop paper on EBMs for programming. Silver sponsor. We're hiring!
   
1 August 2021
INTERSPEECH 2021

INTERSPEECH 2021, hybrid event, Brno, Czech Republic

30th August - 3rd September 2021, hybrid event, physically in Brno, Czech Republic, and also virtually.
3 accepted papers
   
30 August 2021
ICML2021

International Conference on Machine Learning (ICML) 2021

18th-24th July 2021
Demonstration-conditioned reinforcement learning for few-shot imitation
18 July 2021
blank

International ACM SIGIR Conference on Research and Development in Information Retrieval 2021

11th - 15th July 2021, online.
NAVER presenting 4 papers accepted at SIGIR, 2 from NAVER LABS Europe. Gold level sponsor.
   
11 July 2021

BE THE FIRST TO KNOW

Subscribe to receive the NAVER LABS newsletter directly in your inbox


LeBenchmark: a reproducible framework for assessing self-supervised representation learning from speech

Solene Evain, Ha Nguyen, Hang Le, Marcely Zanon Boito, Salima Mdhaffar, Sina Alisamir, Ziyi Tong, Natalia Tomashenko, Marco Dinarelli, Titouan Parcollet, Alexandre Allauzen, Yannick Esteve, Benjamin Lecouteux, Francois Portet, Solange Rossato, Fabien Ringeval, Didier Schwab, Laurent Besacier

Interspeech, Brno, Czech Republic, 30 August-3 September 2021

Impact of encoding and segmentation strategies on end-to-end simultaneous speech translation

Ha Nguyen, Yannick Estève, Laurent Besacier

Interspeech, Brno, Czech Republic, 30 August - 3 September 2021

Do multilingual neural machine translation models contain language pair specific attention heads?

Zae Myung Kim, Laurent Besacier, Vassilina Nikoulina, Didier Schwab

Findings of the Annual Meeting of the Association for Computation Linguistics (ACL) 2021, virtual event, 1-6 August, 2021

Lightweight adapter tuning for multilingual speech translation

Hang Le, Juan Pino, Changhan Wang, Jiatao Gu, Didier Schwab, Laurent Besacier

The Annual Meeting of the Association for Computation Linguistics (ACL) 2021, virtual event, 1-6 August, 2021
DCRL A new family of approaches to few-shot imitation

A new family of approaches to few-shot imitation

A new approach to learning few-shot imitation agents whereby you simply feed demonstrations of a new test task to the learned policy called DCRL. This new approach has several advantages.

blank

SPLADE – a sparse bi-encoder BERT-based model achieves effective and efficient first-stage ranking

A new sparse bi-encoder BERT-based model for effective and efficient first-stage ranking. The first to rival dense models.  

blank

Continual learning of visual representations without catastrophic forgetting

Using domain randomization and meta-learning, computer vision models forget less when exposed to training samples from new domains. Remembering is a crucial element in the deployment of self-driving cars and robots which interact in dynamic environments.

GLOBAL AI R&D BELT

ACADEMIA – EU/GOVT – ENTREPRENEURS

Our partnerships range from long-term fundamental research to investment in products and services.

This web site uses cookies for the site search, to display videos and for aggregate site analytics.

Learn more about these cookies in our privacy notice.

blank

Cookie settings

You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.

FunctionalThis website uses functional cookies which are required for the search function to work and to apply for jobs and internships.

AnalyticalOur website uses analytical cookies to make it possible to analyse our website and optimize its usability.

Social mediaOur website places social media cookies to show YouTube and Vimeo videos. Cookies placed by these sites may track your personal data.

blank