NAVER LABS Europe Homepage
A DISTRIBUTIONAL
APPROACH TO
CONTROLLED TEXT
GENERATION
A SCALABLE TRANSFORMER ARCHITECTURE
FOR SUMMARIZING LONG DOCUMENTS
METHODS FOR VISUAL LOCALIZATION
Slider
ICLR 2021

International Conference on Learning Representations (ICLR) 2021

Orals, posters, socials and workshops ICLR2021 by NAVER LABS Europe and NAVER AI LAB.    
3 May 2021
a distributional approach to controlled text generation

Blog: 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.
30 April 2021
RpAd logo

Seminar: Perceptual robot learning

20th May 2021
Speaker: David Held, assistant professor at Carnegie Mellon University in the Robotics Institute and director of the RPAD lab: Robots Perceiving And Doing.
Virtual seminar. Please register.
20 May 2021
ICRA 2020

2020 International Conference on Robotics and Automation (ICRA)

31st May - 4th June 2020, online. Fast Adaptation of Reinforcement-Learned Robot Navigation Skills to Human Preferences,  Jinyoung Choi, Christopher Dance et al.
31 May 2020

BE THE FIRST TO KNOW

Subscribe to receive the NAVER LABS newsletter directly in your inbox


Continual adaptation of visual representations via data augmentation and meta-learning

Riccardo Volpi, Diane Larlus, Gregory Rogez

Computer Vision and Pattern Recognition (CVPR 2021), virtual event, 16-25 June, 2021

Probabilistic embeddings for cross-modal retrieval

Sanghyuk Chun, Seong Joon Oh, Rafael Sampaio de Rezende, Yannis Kalantidis, Diane Larlus

Computer Vision and Pattern Recognition (CVPR 2021), virtual event, 16-25 June, 2021

An empirical study of end-to-end simultaneous speech translation decoding strategies

Ha Nguyen, Yannick Estève, Laurent Besacier

The International Conference on Acoustics, Speech, & Signal Processing (ICASSP), Toronto, Canada, 6-11 June, 2021

Risk conditioned distributional soft actor-critic for risk-sensitive navigation

Jinyoung Choi, Christopher Dance, Jung-eun Kim, Seulbin Hwang, Kyung-sik Park

International Conference on Robotics and Automation (ICRA), Xi’an, China, 30 May - 5 June, 2021
a distributional approach to controlled text generation

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.

blank

NAVER LABS Europe @ EACL2021

Papers and activities of NAVER LABS Europe at EACL 2021. NLG, scaling to larger context, cost of supervised data, controlling the output plus ASR at the AfricaNLP workshop. 

blank

A scalable Transformer architecture for summarizing long documents

Our Global BERT-based Transformer architecture fuses global and local information at every layer, resulting in a reading comprehension model that achieves a deeper understanding for long documents and enables flexibility for downstream tasks.

GLOBAL AI R&D BELT

ACADEMIA – EU/GOVT – ENTREPRENEURS

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