←
Project Aria @Meta201 posts
Project Aria @Meta avatar

Project Aria @Meta

@meta_aria

Project Aria is a research tool from Meta Reality Labs, to help build the future responsibly.

◷ Joined June 2023▧ 68 Photos and videos
Project Aria @Meta avatar
Project Aria @Meta@meta_aria·Oct 8

Excited to share our latest collaboration with the @ComputerHistory Museum and Lighthouse Guild (@lighthousegld ) to redefine accessible cultural experiences! 🏛️🤖 Through an early prototype using Project Aria research glasses, we’re exploring how Conversational AI Guides and Spatial Audio Navigation can make museum tours deeply engaging and truly inclusive—especially for blind and low vision visitors. By grounding technological innovation in community-led research, we’re building a more accessible future for spatial computing. Read the full update on our blog: computerhistory.org/blog/ai-…

3:44
Project Aria @Meta avatar
Project Aria @Meta@meta_aria·3h

Mark your calendars for Friday Nov. 20th to apply to join the Project Aria team at the 2027 Reality Hack at MIT. ✈️

Mark your calendars. Reality Hack is back, Jan. 28 to Feb. 1, 2027. In 2027, our theme is "Human After All." Applications open on Friday, Nov. 20. Sign up for our newsletter to be the first to know when applications open at realityhackatmit.com/

Post attachment
Reality Hack at MIT avatar
⟳ Project Aria @Meta retweeted
Reality Hack at MIT@realityhackmit·Nov 17

Mark your calendars. Reality Hack is back, Jan. 28 to Feb. 1, 2027. In 2027, our theme is "Human After All." Applications open on Friday, Nov. 20. Sign up for our newsletter to be the first to know when applications open at realityhackatmit.com/

Post attachment
Chaitanya Patel avatar
⟳ Project Aria @Meta retweeted
Chaitanya Patel@chaitanya100100·Nov 9

Can a human motion prior help egocentric SLAM, and can SLAM in turn help egocentric motion reconstruction? Presenting EgoMo3R, our #NeurIPS2026 paper on joint 3D motion and scene reconstruction from egocentric video. chaitanya100100.github.io/Eg…

0:08
Project Aria @Meta avatar
Project Aria @Meta@meta_aria·Nov 10

Teaching robots new tricks used to take forever. Now it takes under 5 minutes. 🦾⏱️ Meet "Steertuning" from the NYU team, a new method that adapts robot policies to new environments using just 5 human video demos. Our favorite detail shouted out in the paper? The massive 100+ hour egocentric dataset powering their base model was captured on Aria Gen 2 glasses. 😎🕶️ Check it out and see the bots in action: steertuning.github.io/ Code: github.com/billy-yibo-yan/st…

As we get closer to a world where we live among robots, it’s becoming more and more valuable for robots to learn quickly with and from people. I’m very excited to share Steertuning, a novel approach that adapts robots to new tasks from 5 human demonstrations in under 5 minutes, from demonstration to deployment. Website: steertuning.github.io/ Code: github.com/billy-yibo-yan/st…

2:08
Alfred Cueva avatar
⟳ Project Aria @Meta retweeted
Alfred Cueva@alfie14x·Nov 10

For Human2Any we were fortunate to use the Aria glasses @meta_aria ! Check the featured post

Congrats to the team at Georgia Tech who built Human2Any - human2any.github.io/ Human2Any learns object-centric interaction priors from human videos, composes them with robot-side feasibility reasoning and motion planning, and deploys them on a Franka arm and an RBY-1 humanoid mobile robot without real-world robot training data. 🤖 human2any.github.io/

Post attachment
Irmak Guzey avatar
⟳ Project Aria @Meta retweeted
Irmak Guzey@irmakkguzey·Nov 9

As we get closer to a world where we live among robots, it’s becoming more and more valuable for robots to learn quickly with and from people. I’m very excited to share Steertuning, a novel approach that adapts robots to new tasks from 5 human demonstrations in under 5 minutes, from demonstration to deployment. Website: steertuning.github.io/ Code: github.com/billy-yibo-yan/st…

2:08
Shuo Cheng avatar
⟳ Project Aria @Meta retweeted
Shuo Cheng@ShuoCheng94·Nov 7

What should transfer from a human video to a robot? Human2Any learns how objects interact, then adapts that knowledge through test-time reasoning and planning. Accepted to #CoRL2026! I'll be presenting in person next week—come say hi! human2any.github.io (1/n)

1:36
Project Aria @Meta avatar
Project Aria @Meta@meta_aria·Nov 9

Congrats to the team at Georgia Tech who built Human2Any - human2any.github.io/ Human2Any learns object-centric interaction priors from human videos, composes them with robot-side feasibility reasoning and motion planning, and deploys them on a Franka arm and an RBY-1 humanoid mobile robot without real-world robot training data. 🤖 human2any.github.io/

Post attachment

What should transfer from a human video to a robot? Human2Any learns how objects interact, then adapts that knowledge through test-time reasoning and planning. Accepted to #CoRL2026! I'll be presenting in person next week—come say hi! human2any.github.io (1/n)

1:36
Jacob Van Meter avatar
⟳ Project Aria @Meta retweeted
Jacob Van Meter@jacobvm04·Nov 3

when LaMAria was introduced a year ago, Meta's closed-source Aria SLAM was far ahead of academic systems. one year later, we've surpassed it in 3/5 categories: medium, long, and low light. here's what closing that gap looks like:

0:17

wow @jacobvm04 and i just took first place on one of robotics’ hardest problems. machines knowing where they are in the world. slam dunk.

Post attachment
Edward Miller avatar
⟳ Project Aria @Meta retweeted
Edward Miller@TweetEdMiller·Nov 3

Kudos to the researchers closing the gap between academic and industrial SLAM. One of the reasons the team made @meta_aria available to external researchers was to shift attention towards the higher level problems that are unlocked once you take accurate & precise location as a given. If SLAM tells us where a device is, we can begin to build a shared understanding for the environment, how the world changes, and how it will change with interventions. That's where things get really interesting and where I hope to see more people explore.

when LaMAria was introduced a year ago, Meta's closed-source Aria SLAM was far ahead of academic systems. one year later, we've surpassed it in 3/5 categories: medium, long, and low light. here's what closing that gap looks like:

0:17
Project Aria @Meta avatar
Project Aria @Meta@meta_aria·Nov 2

The setup: Project Aria glasses (Gen 1 & Gen 2) capture first-person video, and two 8-channel EMG armbands record forearm muscle activity and IMU from both arms. That's 100 hours of synchronized video, EMG, IMU and audio, all unscripted.

Project Aria @Meta avatar
Project Aria @Meta@meta_aria·Nov 2

Teaching vision models how actions feel, not just how they look. 👓💪 Congratulations to our partners at the University of Maryland on their paper accepted to #NeurIPS2026! Introducing MotorSense, the first large-scale multimodal dataset pairing egocentric video with surface EMG. Spanning 100 hours of unscripted hand manipulation captured using Project Aria glasses and bimanual EMG armbands, MotorSense bridges the gap between visual perception and physical motor intent. Explore the dataset and paper: 🔗 cs.umd.edu/~edessale/motorse…

0:04
Project Aria @Meta avatar
Project Aria @Meta@meta_aria·Oct 20

Exciting work from the #EgoXperience team! 🚀 They are turning human experience into world-grounded representations for embodied AI. By utilizing both simulated data from the Aria Synthetic Environments dataset and real-world data like the Aria Digital Twin dataset, their 1.2B parameter EgoX model achieves impressive single-pass joint reconstruction of scenes, hands, and objects from just monocular observations. 🕶️🌐 Read the paper and check out the data: ropedia.github.io/EgoXperien…

😎Learning World-Grounded Egocentric Representations from Human Experience😎 #EgoXperience is a full-stack framework for jointly reconstructing camera motion, scene geometry, hands, and objects in a shared 3D world - Page: ropedia.github.io/EgoXperien… - Code: github.com/Ropedia/EgoXperie…

2:40