ADen: Adaptive Density Representations for Sparse-view Camera Pose Estimation: https://
go.fb.me/9brdhb
@aiatmeta
-
ADen: Adaptive Density Representations for Sparse-view Camera Pose
By
–
-
Controllable Human-Object Interaction Synthesis Technology
By
–
5️⃣ Controllable Human-Object Interaction Synthesis: https://t.co/MUgJzFR3dU pic.twitter.com/sWuMrefWYi
— AI at Meta (@AIatMeta) 3 octobre 2024Controllable Human-Object Interaction Synthesis: https://
go.fb.me/dcgygy -
Sapiens: Foundation for Human Vision Models
By
–
4️⃣ Sapiens: Foundation for Human Vision Models: https://t.co/1J1KosoP1Z pic.twitter.com/mnjL92d1OA
— AI at Meta (@AIatMeta) 3 octobre 2024Sapiens: Foundation for Human Vision Models: https://
go.fb.me/5uksso -
CGPO: Mixture of Judges Outperforms RLHF Approaches
By
–
New paper from GenAI and Meta FAIR. CGPO uses Mixture of Judges and consistently outperforms SOTA RLHF approaches across various tasks. More details and key results in the full thread
-
Llama Stack Official Distribution: Unified API for Multiple Providers
By
–
We’re excited to share the first official distribution of Llama Stack! It packages multiple API Providers into a single endpoint for developers to enable a simple, consistent experience to work with Llama models across a range of deployments. Details https://
go.fb.me/xfi7g3 -
Meta Awards First Open Source AI Grants for Global Challenges
By
–
1yr ago we began seeking proposals from around the world to use open source AI to address global challenges. Now, we're excited to announce the recipients of our first grants ranging from education projects in India to healthcare in Sub-Saharan Africa https://
go.fb.me/pd36be -
Meta Research Showcases Latest AI and Vision Work at ECCV2024
By
–
We’re on the ground at #ECCV2024 in Milan this week to showcase some of our latest research, new research artifacts and more. Here are things you won’t want to miss from Meta FAIR, GenAI and Reality Labs Research this week whether you’re here in person or following from your
-
New Llama 3.2 Vision Models and Complete Collection Details
By
–
Details on Llama 3.2 11B & 90B vision models — and the full collection of new Llama models
-
Gratitude for Llama Track Fireside Chat at Connect
By
–
Thank you both for the great fireside chat for our first-ever Llama track at Connect!