Meta AI

Want to explore the wav2vec pretrained models or play with the code? You’re in luck! It’s all open source. Create your own positive #Impact on language here: http://ow.ly/THMC50HyqG2.

Learn more about our researchers Wei-Ning Hsu and Michael Auli, wav2vec, and their positive #Impact at http://ow.ly/FF6n50HyqET.

Out of the world’s 7,000 languages, #SpeechRecognition works well for only a small fraction. Wav2vec and #AI are changing that. Self-supervision and less reliance on labeled data can make speech tech more accessible and a key to the #metaverse. Learn how at https://ai.facebook.com/research/impact/wav2vec

Learn more about Meta's AI Research SuperCluster (RSC), our latest AI supercomputer for AI research. http://ow.ly/4khz50Hzlvu

Meta is announcing the AI Research SuperCluster (RSC), our latest AI supercomputer for AI research. RSC will allow our researchers to do new, groundbreaking experiments in AI. We believe that by mid-2022 it will be the fastest AI supercomputer in the world. Learn more about RSC and the important role it will play: http://ow.ly/JMF550HzpqI

We’ve built data2vec, the first general high-performance self-supervised algorithm for speech, vision, and text. We applied it to different modalities and found it matches or outperforms the best self-supervised algorithms. We hope this brings us closer to a world where computers can learn to solve many different tasks without supervision. Learn more and get the code: https://ai.facebook.com//the-first-high-performance-self-s

Health, the environment, language. When cutting-edge #AI research tackles real world problems, positive change happens. Let’s build the future of AI, together. Learn how our researchers are making an #Impact at http://ow.ly/eY1z50HyqBK.

To help build more versatile & robust AI speech recognition tools, we are announcing Audio-Visual HuBERT (AV-HuBERT), a state-of-the-art self-supervised framework for understanding speech that learns by observing & hearing people speak. Learn more and get the code: https://ai.facebook.com//ai-that-understands-speech-by-loo

We’re sharing results of the Image Similarity Challenge, an open research competition to create better systems to identify manipulated images. We’re also sharing a unique million-image data set created by Meta AI. Learn more: https://ai.facebook.com//detecting-manipulated-images-the-

Do you know a child who loves to draw? Have you ever wished that characters in their drawings could come to life and move around the page? Using AI, we have developed automatic animation that can bring children’s one-of-a-kind characters to life! Learn more about this research, and submit your child’s drawing to check it out: http://ow.ly/r5CN50HcoF4

Correction - Here are today's workshops from our own Meta AI researchers at #NeurIPS2021. For the full schedule, visit our website: https://ai.facebook.com/events/neurips2021/

Want to hear from Meta AI researchers? Attend one of our #NeurIPS2021 workshops today! For the full schedule, visit our website: https://ai.facebook.com/events/neurips2021

Congratulations to Noam Rozen, Aditya Grover, Maximilian Nickel & Yaron Lipman on winning Outstanding Paper at #NeurIPS2021. Hear from them today at 4 p.m. PST.

Here's where you can find Meta AI researchers at #NeurIPS2021 today. For the full schedule, visit our website: https://ai.facebook.com/events/neurips2021