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 advancing in the frontiers of AI in robotics and is further exploring touch sensitivity.
Facebook AI released Captum 0.4 with new functionality for model understanding.
IC-GAN can be used with both labelled and unlabelled datasets.
A lower temperature causes repetitive sentences, while a medium temperature makes sentences locally coherent.
GSLM uses the latest breakthroughs in representation learning, allowing it to work directly from raw audio signals, without any text or labels.
Facebook’s AI-based content moderation algorithm removed over 33 million pieces of content between June 16 and July 31 in India.
VICReg combines the variance term with a decorrelation mechanism based on redundancy reduction and covariance regularisation.
Few-shot NAS enables users to quickly design a powerful customised model for their tasks using just a few GPUs.
AugLy combines modalities like audio, video, image and text, to help algorithms better understand and deal with complex content.
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’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 […]