Facebook AI
@facebookai

Facebook AI focuses on bringing the world together by advancing AI, powering meaningful and safe experiences, and conducting open research.




Facebook AI    @facebookai
Facebook AI has released DrQ-v2, a model-free #reinforcementlearning algorithm for visual continuous control. DrQ-v2 yields state-of-the-art results by using data augmentation to learn directly from pixels. Learn more and get the code:

Facebook AI    @facebookai
We’ve developed a new computer vision model called ConViT, which combines two widely used AI architectures convolutional neural networks (CNNs) & Transformer-based models in order to overcome some important limitations of each approach on its own. https://t.co/NlCJ6NMNox

Facebook AI    @facebookai
We’re sharing our work on few-shot neural architecture search (NAS), which combines the accuracy of vanilla NAS with the speed & efficiency of one-shot NAS. Few-shot NAS lets anyone design a powerful custom model quickly, with just a few GPUs. Learn more: https://t.co/fdUTFSmMK3

Facebook AI    @facebookai
We’ve built and open-sourced BlenderBot 2.0, the first #chatbot that can store and access long-term memory, search the internet for timely information, and converse intelligently on nearly any topic. It’s a significant advancement in conversational AI. https://t.co/H17Dk6m1Vx

Facebook AI    @facebookai
We’ve developed two methods to significantly improve the accuracy of supernets, which have emerged as a powerful way to make network architecture search more efficient. AttentiveNAS and AlphaNet deliver state-of-the-art results on the ImageNet data set. https://t.co/RHEpU1A0S2

Facebook AI    @facebookai
We’re excited to see how the AI research community builds on RMA and will be sharing our research at #RSS2021. Learn more: https://t.co/QbmlGfg3RS

Facebook AI    @facebookai
After being trained entirely in simulation, an RMA-enabled robot is then deployed in the real world, where its base policy and adaptation module work asynchronously to enable it to adapt in real time.

Facebook AI    @facebookai
Researchers from Facebook AI, @berkeley_ai, and @SCSatCMU have developed #AI that can enable a legged robot to adapt in fractions of a second to changing conditions in the real world.

Facebook AI    @facebookai
(resharing w/correct link!) We’re using the natural association between video & sound to teach machines to better understand the world. Our self-supervised approach (a #CVPR21 best paper candidate) learns directly from sounds & images in videos. https://t.co/QHXtgklJGy

Facebook AI    @facebookai
We’re sharing new research on using the natural association between video & sound to teach machines to better understand the world. Our self-supervised approach, which is a #CVPR21 best paper candidate, learns directly from sounds & images in videos. https://t.co/Wp6sYXwBHe

Facebook AI    @facebookai
We’re sharing a new theory that attempts to explain one of the mysteries of #deeplearning: why so-called non-contrastive self-supervised learning often works well. Learn more: https://t.co/mVgxbBUcnB

Facebook AI    @facebookai
We released DensePose-CSE, a #detectron2 framework for predicting dense correspondences for people and animals within and across categories in one go. Learn more: https://t.co/Ph5Fo55bbq
 Reply      Retweet   10      Like    35   

Facebook AI    @facebookai
Here is the first method to enable freestyle dance generation in high-resolution from any single image using Generative Adversarial Networks (GANs). Let’s dance! https://t.co/277XkPEtZH

Facebook AI    @facebookai
We presented an approach to allow scalable learning of single image 3D reconstruction, using in-the-wild image collections in a ‘shelf-supervised’ manner: https://t.co/KYiIXdnnS1

Facebook AI    @facebookai
At #CVPR2021, Facebook AI pushed the state of the art in many important areas of #CV, including 3D reconstruction, image manipulation, cross-modal learning and more. Here are some highlights:

Facebook AI    @facebookai
We're sharing details on our newest, cutting-edge AI advancements that provides a deeper, more nuanced understanding of product attributes. Read more: https://t.co/3wGUCwoPJL

Facebook AI    @facebookai
We’re sharing significantly improved Mask R-CNN baselines that match recent SOTA results from other #computervision experts. We’re also providing an analysis of what drove these gains & adding recipes to our open source Detectron2 object detection library. https://t.co/BDMR8XijES
 Reply      Retweet   82      Like    342   

Facebook AI    @facebookai
We are 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 #CVPR2021. Learn more: https://t.co/XqSDbCoX7v

Facebook AI    @facebookai
In collaboration with @ntu_spml, @LTIatCMU, & @jhuclsp we introduce SUPERB, a benchmark using 10 speech processing tasks to standardize evaluations of #unsupervised models used in speech processing advancements. Submit & evaluate your models here: https://t.co/AIjx3IoZLt
 Reply      Retweet   51      Like    176   

Facebook AI    @facebookai
We're open-sourcing XCiT, a new Transformer-based #computervision model with linear (not quadratic) complexity. XCiT, created in partnership w/ @inria researchers, processes high-res images extremely efficiently & delivers strong performance. Code & models https://t.co/7aRHfNxOp6
 Reply      Retweet   126      Like    536   

Facebook AI    @facebookai
We are 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. Learn more: https://t.co/G7DhxRgfC5
 Reply      Retweet   98      Like    268   

Facebook AI    @facebookai
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. Read more: https://t.co/w1FBLKMUFh
 Reply      Retweet   370      Like    1051   

Facebook AI    @facebookai
The simplicity and stability of HuBERT open the door for research on analyzing learned representations and broader adoption in the speech and NLP communities. The quality of the learned presentations facilitates deployment for many different downstream speech applications.

Facebook AI    @facebookai
HuBERT either matches or improves upon the SOTA speech representation methods for the standard Libri-light and Librispeech benchmarks. Also, discrete HuBERT representations achieve SOTA performance for Spoken Language Modeling and compression with an impressive rate of 365bps.

Facebook AI    @facebookai
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. Learn more: https://t.co/0eF3emyKYu
 Reply      Retweet   95      Like    303   

Facebook AI    @facebookai
TextStyleBrush is the first self-supervised AI model that replaces text in existing images of both scenes & handwriting in one shot using just a single word. Read more: https://t.co/0QfLraAQvV
 Reply      Retweet   51      Like    253   

Facebook AI    @facebookai
We are releasing ACCENTOR, a new data set that combines contextual chit-chat and traditional task-oriented dialogs. Automatic & human evaluations show our models can code-switch seamlessly, making virtual assistant conversations more natural & interactive. https://t.co/HjOzZkpLfC
 Reply      Retweet   45      Like    171   

Facebook AI    @facebookai
Today, we’re introducing TextStyleBrush, the first self-supervised AI model that replaces text in existing images of both scenes and handwriting in one shot using just a single example word: https://t.co/0QfLraAQvV
 Reply      Retweet   364      Like    1551   

Facebook AI    @facebookai
The first fully documented and supported release for FairScale. FairScale makes available the latest distributed training techniques in the form of composable modules and easy to use APIs for optimizing training and scaling your models. Check it out: https://t.co/atUHZnGWOM
 Reply      Retweet   33      Like    152   

Facebook AI    @facebookai
We’ve developed an AI framework that helps filmmakers guide an aerial drone to record just the right kind of shot. Tell it whether you want a very exciting video clip or something calm & the system picks the trajectory and camera angle. Learn more: https://t.co/yhSAvHpIhk
 Reply      Retweet   53      Like    211   

Facebook AI    @facebookai
Facebook AI’s new open source speech recognition model, wav2vec Unsupervised, uses no transcribed data at all. We’ve tested it on many languages, such as Swahili, that have proven challenging for other systems. Learn more in our blog post here: https://t.co/b6ic50AsM6
 Reply      Retweet   174      Like    691   











 








Facebook AI

Sergey Levine

Aran Komatsuzaki

Google AI

hardmaru

DeepMind