Highlights of uCO3D:
• 170K videos depicting diverse objects from all directions.
• Objects spanning ~1000 categories — grouped into 50 super-categories.
• Full original videos annotated with object segmentation, camera poses & point clouds.
• 3D Gaussian Splat
@aiatmeta
-
uCO3D: 170K Videos with 3D Annotations for Object Recognition
By
–
-
Meta PARTNR Demo: Insights and Challenges in Human-Robot Collaboration
By
–
By sharing some of the insights and challenges in developing the Meta PARTNR demo, we hope to contribute to the development of the next wave of innovation in human-robot collaboration. Research paper https://
go.fb.me/prlg14
Dataset and code https://
go.fb.me/k9dzc0 -
Blended Labs Uses Llama Models for Personalized AI-Native Learning
By
–
Blended Labs, an EdTech company in Germany, is using Llama 3.1 + 3.2 models to enable a wide range of AI-native flows for personalized learning pathways, real-time feedback, instant educational content generation and social gamification
-
Meta FAIR Brain-to-Text Decoding via Non-invasive Typing Method
By
–
Research paper from Meta FAIR and @bcbl_ researchers – Brain-to-Text Decoding: A Non-invasive Approach via Typing ➡️ https://t.co/6FXpmNiEgJ pic.twitter.com/AGxkr0vS9Z
— AI at Meta (@AIatMeta) 3 mars 2025Research paper from Meta FAIR and @bcbl_ researchers – Brain-to-Text Decoding: A Non-invasive Approach via Typing https://
go.fb.me/o8rhmv -
Llama and IBM Launch AI Scout Advisor for Sevilla FC
By
–
Llama is giving @SevillaFC an edge in scouting the next wave of soccer stars. Together with IBM they created Scout Advisor — a generative AI-driven scouting tool designed and built on watsonx, with Llama 3.1 https://
go.fb.me/gbx2h5 -
Meta PARTNR: Benchmark for Multi-Agent Planning and Reasoning
By
–
Meta PARTNR is a benchmark for planning and reasoning in embodied multi-agent tasks. This large-scale human and robot collaboration benchmark was core to our recent demos and also informs our work as scientists and engineers pushing this field of study forward. pic.twitter.com/bM1ghMXeS2
— AI at Meta (@AIatMeta) 25 février 2025Meta PARTNR is a benchmark for planning and reasoning in embodied multi-agent tasks. This large-scale human and robot collaboration benchmark was core to our recent demos and also informs our work as scientists and engineers pushing this field of study forward.
-
EgoMimic: Georgia Tech’s Framework for Humanoid Robot Development
By
–
Inspired by Project Aria and Ego-Exo4D from Meta FAIR, researchers at @GeorgiaTech developed EgoMimic, a new algorithmic framework that utilizes human data and robot data for humanoid robot development ➡️ https://t.co/tYZOVwgYYm pic.twitter.com/D0EHF58vZF
— AI at Meta (@AIatMeta) 25 février 2025Inspired by Project Aria and Ego-Exo4D from Meta FAIR, researchers at @GeorgiaTech developed EgoMimic, a new algorithmic framework that utilizes human data and robot data for humanoid robot development https://
go.fb.me/96j5ba -
Audiobox Aesthetics: Unified Quality Assessment for Audio
By
–
Audiobox Aesthetics is a model for unified automatic quality assessment for speech, music and sound. Try the demo on @huggingface https://
go.fb.me/fq6brx -
Meta Democratizes Language Technology with UNESCO Partnership Program
By
–
In support of @UNESCO
’s work, we’re inviting collaborators to join us in democratizing language technology and building more inclusive AI systems with the Language Technology Partner Program https://
go.fb.me/ccrklu -
Meta FAIR Research Evolution: Open Source Human-Robot Collaboration
By
–
A closer look at the evolution of the research from Meta FAIR that led to our latest open source work for human-robot collaboration. Details on Meta PARTNR https://
go.fb.me/ufdanx