Project Aria is a research tool from Meta Reality Labs, to help build the future responsibly.
Seattle, WA
Joined June 2023
- Tweets188
- Following167
- Followers2.1K
- Likes315
Pinned Tweet
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-…
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…
We’ve partnered with the Computer History Museum to build an AI-guided museum tour experience! 👓✨ Read the full blog post to learn more about the future of accessible museum experiences:
computerhistory.org/blog/ai-… youtu.be/RlXisxLm8lM?si=ybfv…
Using Project Aria research glasses, this early demo explores how Spatial Audio Navigation and a Conversational AI Guide can make museums more engaging, personal, and accessible to everyone. This includes research alongside blind and low vision communities in partnership with Lighthouse Guild.
👉@lighthousegld
Together with @ComputerHistory, we’re shaping the future of discovery and inspiring the next generation of innovators.
Check out CoMind, an ECCV 2026 dataset exploring how people collaborate, from two participants; perspectives!
Captured with Project Aria glasses, CoMind combines synchronized egocentric video, gaze, audio, and 3D scans to study shared attention, anticipate interactions, and predict handovers. A rich resource for building AI that understands and supports human collaboration.
Fantastic work by the CoMind team! 📷 @xiwang1212
🚀 New from our team: CoMind (comind.ethz.ch/) - a dataset for AI that understands not just what I am doing, but what WE are doing together.
Two people. Two egocentric views. Gaze. Speech. 3D scenes. Social cues.
Accepted at #ECCV2026 🧵👇
You can now watch the entire Fifth Hands-On Egocentric Research Tutorial with Project Aria from Meta from ECCV 2026!
11 talks from the brilliant minds behind Boxer, LAMP, Eye Tracking on Aria Gen 2, plus some amazing partner work from University of Maryland, ETH Zurich, TUM, and more. 💡
youtube.com/playlist?list=PL…
Project Aria @Meta retweeted
🚀 New from our team: CoMind (comind.ethz.ch/) - a dataset for AI that understands not just what I am doing, but what WE are doing together.
Two people. Two egocentric views. Gaze. Speech. 3D scenes. Social cues.
Accepted at #ECCV2026 🧵👇
Aria Gen 2 Glasses spotted in the wild! 😎
I know teleoperation is old these days but it feels magical when you could teleoperate a humanoid just by wearing a pair of classes (bonus: the robot also sees from glasses too!)
Of course we don't stop here --- we are working on a system to train robots with everyday human experience, without any teleop data. More to come!
Kudos to the team Chuye Zhang @DanielZhenyang @ChuizhengKong
Check out the latest updates from Project Aria, now live from ECCV 2026 in Malmö, Sweden.✨
youtu.be/EM6NytIoTg0?si=0fpR…
Check out the latest talk from @rapideRobot delivered at ECCV 2026 in Malmö, Sweden earlier this month.
👉"Human Behavior for Research in the Era of Egocentric Devices"
youtu.be/lmqLgf1ItVw?si=ZCW1…
Check out TrackEverything from CMU Robotics. 💡
TrackEverything is a Long-term 3D point tracking method (1000+ frames), using depth and camera pose to see the world in a stable coordinate system. TrackEverything is especially effective for egocentric capture setups like Project Aria glasses.
Amazing work by @ayushjain1144 while interning with @AdamWHarley at Meta. 🚀
1/ We introduce TrackEverything: a 3D point tracker that tracks all points across all frames of long videos (1000+ frames).
Our key idea is to tie computation to unique 3D scene content rather than redundant 2D pixels in a video.
trackeverything.github.io
Project Aria @Meta retweeted
1/ We introduce TrackEverything: a 3D point tracker that tracks all points across all frames of long videos (1000+ frames).
Our key idea is to tie computation to unique 3D scene content rather than redundant 2D pixels in a video.
trackeverything.github.io
Heading to #ECCV2026? Join us for the Fifth Hands-On Egocentric Research Tutorial — a half-day, hands-on deep dive into egocentric data with Project Aria.
📍Palissad West, Floor 0 (must take the stairs)
Tue, Sept 8
9AM–12:30PM
Can’t make it to Sweden? We’ll post the whole session on YouTube after the conference.
projectaria.com/project_aria…
Richard Newcombe is kicking us off with an inspiring keynote in Pallisad West!
🗣️@rapideRobot
Project Aria @Meta retweeted
Plans for today @eccvconf #ECCV2026
You can catch me today if interested...
9:40 OpenSUN3D - Modelling in an EgoSensed World
11:30 ACVR - Towards a Future of Wearable Assistance
15:00 3D Humans - Ego Vision Towards a 3D Human
Or @JacobChalkie at 10:15 @meta_aria Tutorial
Project Aria @Meta retweeted
EgoWAM has been accepted to #CoRL2026 @corl_conf 🥳🥳 See you all in Austin!!!!
We’ve also open-sourced all the data and code:
📊 Data: partners.mecka.ai/egoverse?t…
💻 Code: github.com/GaTech-RL2/EgoWAM…
If you run into any problems, please submit an issue on GitHub. We’ll do our best to address it as soon as possible!
Egocentric human data is abundant, but human motion is not always positive supervision for robot policy due to embodiment gaps. Naive BC co-training can HURT performance ☹️.
🌟Our key finding in **EgoWAM**: the state-prediction branch of a World Action Model effectively bridges this embodiment gap, enabling robot performance to scale with diverse **in-the-wild** human data.
💡The key question then becomes: what world representation transfers best across embodiments?
👇🏻Let’s take a deep dive into it:
🌐 gatech-rl2.github.io/egowam.…
🧵[1/]