Our latest AI advancements represent fundamental building blocks that could power entirely new future shopping experiences.
June 22, 2021
June 21, 2021
June 23, 2021
Facebook AI’s Georgia Gkioxari, who has received the 2021 Pattern Analysis and Machine Intelligence (PAMI) Young Researcher Award, discusses her work in computer vision.
We’re sharing new details on Facebook’s efforts in the crucial area of responsible AI, including work from our RAI team and from across the company.
Facebook AI is contributing to ongoing work to identify manipulated images and improve the detection of data provenance with the Image Similarity data set and challenge, hosted by DrivenData and recently launched at CVPR 2021.
We’re sharing significantly improved Mask R-CNN baselines that match recent SOTA results from other computer-vision experts. We’re also providing an analysis of what drove these gains and adding recipes to our open source Detectron2 object detection library.
June 18, 2021
Deep neural networks have long been considered too complex to understand from first principles — but new research does just that, presenting a theoretical framework for DNNs.
June 17, 2021
We are now launching the Open Catalyst Challenge, an open AI research competition to build new machine learning models that will help scientists discover new catalysts for efficient, economical green energy storage.
We’ve just open-sourced AugLy, a new Python library that will help AI researchers use data augmentations to evaluate and improve the robustness of their machine learning models.
June 15, 2021
We are releasing pretrained HuBERT speech representation models and code for recognition and generation. By alternating clustering and prediction steps, HuBERT learns to invent discrete tokens representing continuous spoken input.
June 09, 2021
We are excited to launch the NetHack Challenge (@NetHack_LE) with a #NeurIPS2021 competition! NetHack is one of the hardest games ever made and it runs 50-100x faster than other RL challenges of comparable complexity.
June 04, 2021
Today we are open-sourcing FLORES-101, a first-of-its-kind, many-to-many evaluation data set covering 101 languages (10,100 translation directions) from all over the world.
June 02, 2021
Facebook is making PyTorch the default framework for building all our AI and machine learning models. Here’s how PyTorch is already powering the next generation of Facebook experiences, and what the future holds.
Facebook © 2021