In addition to the new model, we’re also releasing the SA-1B dataset, which is 400x larger than any existing segmentation dataset — we hope this work will help accelerate computer vision research and enable entirely new applications.
Get the dataset
@aiatmeta
-
Meta Releases SA-1B Dataset: 400x Larger Segmentation Dataset
By
–
-
Meta Advances Embodied AI with VC-1 and ASC Technologies
By
–
Today, we're sharing two major advancements in our work toward general-purpose embodied AI agents: VC-1 & ASC. We're excited for how this work will help build toward a future where AI agents can assist humans in both the virtual & physical world. Details
-
Meta Launches DataPerf Platform for Data-Centric AI Leaderboards
By
–
Today, Meta researchers together with @MLCommons working group, are launching DataPerf, the first platform for building data & data-centric AI algorithm leaderboards. We're excited for how DataPerf will help to push the data-centric AI field forward
-
Meta AI Newsletter Coming Soon with Latest Research Updates
By
–
The next issue of the Meta AI newsletter is coming soon! This edition includes updates on our latest research and a look at some of the systems in place to support AI at Meta's scale. Subscribe
-
MuAViC Enables Audio-Visual Learning for Superior Speech Translation
By
–
MuAViC makes it possible to use audio-visual learning for highly accurate speech translation. Using MuAViC to train our AV-HuBERT model helped us achieve results outperforming other leading translation models in noisy, challenging settings.
— AI at Meta (@AIatMeta) 27 mars 2023
More ➡️ https://t.co/FUnlg2dUOq pic.twitter.com/X6sGzU8FCWMuAViC makes it possible to use audio-visual learning for highly accurate speech translation. Using MuAViC to train our AV-HuBERT model helped us achieve results outperforming other leading translation models in noisy, challenging settings. More https://
bit.ly/3ZNg76h -
Meta’s Efficient AI Development Ecosystems for Production
By
–
AI development ecosystems are increasingly complex and challenging to maintain. Companies like Meta need to develop highly efficient systems to build, serve and improve AI models for production uses. Here's how we make this work effective + efficient
-
Meta AI Researchers Compare Language Models to Human Brain Function
By
–
Meta AI researchers show how current language models differ from the human brain & highlight the role of long-range & hierarchical predictions.
— AI at Meta (@AIatMeta) 23 mars 2023
Read the open accessed article in Nature ➡️ https://t.co/Kf3CCRiqug pic.twitter.com/aRicxEMx3jMeta AI researchers show how current language models differ from the human brain & highlight the role of long-range & hierarchical predictions. Read the open accessed article in Nature https://
go.nature.com/3ZfH7eK -
Meta’s Paper on Blind Navigation Agents Selected for ICLR 2023
By
–
We're proud to share that our paper on the Emergence of Maps in the Memories of Blind Navigation Agents was selected as one of four outstanding papers for #ICLR 2023 — congratulations @erikwijmans
, @dhruvbatradb & team! ICYMI -
Casual Conversations v2: Dataset for Fair and Robust AI Evaluation
By
–
The Casual Conversations v2 dataset is a consent-driven dataset of recorded monologues to enable researchers to evaluate fairness & robustness of AI models. We hope this work helps teams across the industry in building more inclusive AI & products. More details
-
ESM Atlas Updated with 740M Metagenomic Protein Structures
By
–
The updated ESM Atlas is live now and includes 740M+ metagenomic protein structures + pre-computed ESM2 embeddings for these proteins. We can't wait to see what others in the field are able to do with this expanded resource https://
bit.ly/3YUON5n 3/3