Today we're opening a call for applications for Llama 3.1 Impact Grants! Until Nov 22, teams can submit proposals for using Llama to address social challenges across their communities for a chance to be awarded a $500K grant. Details + application https://
go.fb.me/smw6xc
@aiatmeta
-
Llama 3.1 Impact Grants: $500K for Community Solutions
By
–
-
Discover Latest AI Research with Interactive Experimental Demos
By
–
🆕 Try experimental demos featuring our latest AI research!
— AI at Meta (@AIatMeta) 2 août 2024
• Create video cutouts & apply effects in a few clicks.
• Hear what you sound like in another language.
• Bring drawings to life.
• Create a story w/ AI-generated voices & sounds.
AI Demos ➡️ https://t.co/0ZX7uTyOtW pic.twitter.com/Tsq6f9J2JeTry experimental demos featuring our latest AI research!
• Create video cutouts & apply effects in a few clicks.
• Hear what you sound like in another language.
• Bring drawings to life.
• Create a story w/ AI-generated voices & sounds. AI Demos https://
go.fb.me/39k5c0 -
Meta Wins AlgoPerf Competition in Both Tuning Tracks
By
–
The #AlgoPerf competition was designed to find better training algorithms to speed up neural network training across a diverse set of workloads. We’re proud to share that teams from Meta took first place across both external tuning and self-tuning tracks!
-
Schedule Free approach wins self-tuning track competition
By
–
More on the Schedule Free approach that won the self-tuning track.
-
SAM 2 Demo: One-Click Mask Selection with Multi-Frame Refinement
By
–
One click is all you need (but the SAM 2 demo will let you refine your mask with additional selections on any frame anyway).
-
Meta releases SAM 2 and SA-V dataset for vision research
By
–
Along with the Meta Segment Anything Model 2 (SAM 2), we also released SA-V: a dataset containing ~51K videos and >600K masklet annotations.
— AI at Meta (@AIatMeta) 30 juillet 2024
We’re sharing this dataset with the hope that this work will help accelerate new computer vision research ➡️ https://t.co/PkgCns9qjz pic.twitter.com/j6hDTFWH4bAlong with the Meta Segment Anything Model 2 (SAM 2), we also released SA-V: a dataset containing ~51K videos and >600K masklet annotations. We’re sharing this dataset with the hope that this work will help accelerate new computer vision research https://
go.fb.me/0boivt -
SAM 2 Resource Sharing for Beginners
By
–
Great resource for anyone getting started with SAM 2 — thanks for sharing!
-
SAM 2 Implementation Excitement Across Various Tools
By
–
We're excited to see how SAM 2 is implemented in all kinds of tools!
-
Roboflow Community Reaction to SAM 2 Release
By
–
Can't wait to hear how the Roboflow community likes SAM 2!
-
SAM 2: More Advanced Model Empowers Community Innovation
By
–
SAM enabled such an inspiring wave of innovation across the community — we can't wait to see what the community does with this newer, more advanced SAM 2 model!