Facebook AI Releases XLS-R, Self-Supervised Model For Speech Tasks
XLS-R substantively improves upon previous multilingual models by training on nearly ten times more public data in more than twice as many languages.
Meta Is Cracking The Robotic Space, One Touch At A Time
Meta is advancing in the frontiers of AI in robotics and is further exploring touch sensitivity.
Facebook Gives Away Captum For Free: Its Model Interpretability Library For PyTorch
Facebook AI released Captum 0.4 with new functionality for model understanding.
Facebook Introduces New Image Generation Model Called Instance-Conditioned GAN
IC-GAN can be used with both labelled and unlabelled datasets.
Facebook’s First AI Model Based On Audio
A lower temperature causes repetitive sentences, while a medium temperature makes sentences locally coherent.
Facebook’s Answer To GPT-3, Textless NLP
GSLM uses the latest breakthroughs in representation learning, allowing it to work directly from raw audio signals, without any text or labels.
Understanding The Technology Behind Content Moderation System Of Tech Giants
Facebook’s AI-based content moderation algorithm removed over 33 million pieces of content between June 16 and July 31 in India.
Facebook Researcher’s New Algorithm Ushers New Paradigm Of Image Recognition
VICReg combines the variance term with a decorrelation mechanism based on redundancy reduction and covariance regularisation.
Facebook Introduces Few-Shot Neural Architecture Search
Few-shot NAS enables users to quickly design a powerful customised model for their tasks using just a few GPUs.
The Good, The Bad And The AugLy: Behind Facebook’s Newly Open-Sourced Library
AugLy combines modalities like audio, video, image and text, to help algorithms better understand and deal with complex content.
HuBERT: Facebook’s Latest Approach To Self-Supervised Speech Representation Learning
Facebook AI Research (FAIR) has published a research paper introducing Hidden Unit BERT (HuBERT), their latest approach for learning self-supervised speech representations. According to FAIR, self-supervised techniques for speech recognition are currently limited due to three factors: First, the presence of multiple sound units in each input utterance; secondly, the absence of lexicons of input […]
Facebook Gives Away Its Largest Language Database For Free
Facebook’s AI wing recently announced that it will open-source its FLORES-101 database to allow researchers to benefit from the work and use it to improve multilingual translation models. FLORES-101 is a many-to-many evaluation data set which covers 101 different languages. The database is available, along with a tech report and models, here for free use […]
