MingfeiYan

Meta AR Research

[Project Aria @Meta @meta_aria]

Introducing Depth Estimation with NVIDIA’s FoundationStereo—a new open tutorial and codebase for metric depth sensing using Project Aria Gen 2 devices.

⚡️ Real-time ready (20 FPS)
🤖 Zero-shot generalization
⚡️Stereo image rectification and disparity estimation
🔓 Open Source

Check out the code and tutorial: https://t.co/bHWawwtAbb

🔌@the_shweenz

[Project Aria @Meta @meta_aria]

Meta and Project Aria are headed to Denver for CVPR 2026. ✈️

The Project Aria team will be onsite, highlighting the latest from our program on the future of Contextual AI and Robotics research! 🤖

📍 Denver, Colorado
📅 June 3–7, 2026
🤝Booth 201

We'll see you tomorrow for presentations on the cutting edge of computer vision research across CVPR's workshops and tutorials. See our snapshot agenda below for details!

[The New York Times @nytimes]

Breaking News: Anthropic, the A.I. company behind Claude, filed to go public, setting the stage for a massive IPO. https://t.co/VHkAl8IjUp

[Claude @claudeai]

Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors.

Available today at the same price.

[Project Aria @Meta @meta_aria]

How do we train AI to be a real-world expert? 🛠️🧠

Introducing Ego-EXTRA, a new video-language dataset for Expert-Trainee assistance. Researchers at the University of Catania captured unscripted interactions where experts guide trainees through complex tasks in real-time using Aria Glasses.

👓 50 hours of data
💬 15k+ high-quality VQA sets
✅ RGB + Eye Gaze tracking ✅ Hand keypoints & SLAM ✅ IMU, Magnetometer, & Audio ✅ Natural expert-trainee dialogue
🚲 4 scenarios: Bike Workshop, Kitchen, Bakery, & Assembly

Explore the benchmark: https://t.co/jVaJdqQdj8
Read the paper: https://t.co/bfN0hvMM5O

👉@FrancRagusa, @GMFarinella

[Claude @claudeai]

Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude.

Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.

[Anthropic @AnthropicAI]

Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software.

It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans.
https://t.co/NQ7IfEtYk7

[Felix Rieseberg @felixrieseberg]

Today, we’re releasing a feature that allows Claude to control your computer: Mouse, keyboard, and screen, giving it the ability to use any app.

I believe this is especially useful if used with Dispatch, which allows you to remotely control Claude on your computer while you’re away.

[Danfei Xu @danfei_xu]

Introducing EgoVerse: an ecosystem for robot learning from egocentric human data.

Built and tested by 4 research labs + 3 industry partners, EgoVerse enables both science and scaling

1300+ hrs, 240 scenes, 2000+ tasks, and growing

Dataset design, findings, and ecosystem 🧵

[Umar Iqbal @UmarIqb]

#NVIDIA just released a whole ecosystem for human(oid) motion and robot learning from human data. 🚀🦾

Data, as we all know, is the key to scaling AI models. To accelerate the field of Embodied AI, we have open-sourced a full stack of models and tools to capture, generate, retarget, and simulate human(oid) motion data at scale, along with a massive high-quality dataset and a standard human skeletal representation, SOMA, to make them all seamlessly communicate with each other.

The entire suite is available under the Apache 2.0 license.

1️⃣ SOMA: A universal interface to unify all parametric human body models (SOMA-shape, SMPL, MHR, etc.) into a standard skeletal representation, eliminating the need for custom adapters or model-specific retargeting.
🔗 https://t.co/Xrg672T7Nu

2️⃣ Kimodo: High-fidelity, controllable text-to-motion generation for both humans and humanoid robots.
🔗 https://t.co/2cQKAPfvEU

3️⃣ GEM: A global human pose estimation method from in-the-wild videos, natively compatible with SOMA.
🔗 https://t.co/pV0043jwcO

4️⃣ Bones-SEED: A massive dataset of 150k+ motions in SOMA format, including data already retargeted for the Unitree G1, created with our partners at Bones Studio.
🔗 https://t.co/wxfyZ7S9TJ
🔗 https://t.co/oM5rIMdRi8

5️⃣ SOMA Retargeter: A dedicated tool for seamless motion retargeting from the SOMA skeleton to the Unitree G1.
🔗 https://t.co/jg4DUjWcnw

6️⃣ ProtoMotions: Our high-performance simulation framework for training digital human(oid)s via RL, now with native SOMA support.
🔗 https://t.co/K1zsGEdl5S

This is just the beginning, and we have much more in the pipeline. Excited to see what the community builds next!

#NVIDIA #GTC #GTC2026 #Robotics #EmbodiedAI #PhysicalAI @NVIDIAAI

[TIME @TIME]

TIME’s new cover: How Anthropic found itself in an existential fight over the future of war https://t.co/jztyCZoI18

[Boris Cherny @bcherny]

Claude Code Remote is rolling out now for Pro users

[MingfeiYan @mingfeiy]

@mikeyk Go Claude!

[Mike Krieger @mikeyk]

Claude is #1 in the App Store today — I want to say a huge thank you to all of our new (and existing!) users for the support. We’re working hard for you, please share your thoughts and feedback along the way.

[Anthropic @AnthropicAI]

A statement from Anthropic CEO, Dario Amodei, on our discussions with the Department of War.

https://t.co/rM77LJejuk

[DailyPapers @HuggingPapers]

Meta released ShapeR

Generates metric 3D shapes from casual captures using SLAM points, multi-view images & text captions. 2.7x better Chamfer distance than SOTA on a new benchmark with 178 in-the-wild objects.

[Christian Holz @cholz]

egoPPG: Heart Rate Estimation from Eye-Tracking Cameras in Egocentric Systems to Benefit Downstream Vision Tasks.
Talk in: Project Aria Research Tutorial
ICCV'25 poster: Tuesday
arXiv: https://t.co/WBkuTGozV6
code+dataset: https://t.co/aZm1a7f9ZH
project: https://t.co/rEfItroeIR

[MingfeiYan @mingfeiy]

Project Aria’s mission is to bring the human perspective to AI. Today marks another important milestone - Aria Gen 2 applications are now open to academic and corporate research partners! See our blog post on the Meta blog for more detail. We've also released the brand new Aria Gen 2 Pilot Dataset, which gives a glimpse of what the glasses are capable of producing. Please enjoy learning more about Aria Gen 2 and submit a detailed application when ready. And talk to us at #ICCV2025 if you're here. See links below!

Blog Post: https://t.co/SLfVZtUiq2
Device White Paper: https://t.co/pOsJWvvbbN
Dataset Page: https://t.co/8bBGvYJ0ms
Research Kit Page for Applications: https://t.co/df7cdUvEdd
Documentation: https://t.co/ikPYcZ55CM

[Project Aria @Meta @meta_aria]

Join the Project Aria Team at "Benchmarking Egocentric Visual-Inertial SLAM at City Scale" in room 325B.

📅TODAY! Sunday, Oct. 19
⏰ 1pm-5pm
🔗 Agenda: https://t.co/u1XLHqgYN9

🚨Opening remarks @ 1pm from @jajuengel, @mapo1, and David Caruso.

Learn more about how Project Aria's MPS SLAM + Aria Gen 1 glasses enabled the LaMAria dataset - a city-scale egocentric dataset to track progress in egocentric VIO/SLAM.

[Project Aria @Meta @meta_aria]

The Project Aria Team is excited for The Fourth Hands-on Egocentric Research Tutorial with Project Aria 😎 TOMORROW Monday, Oct 20th

📅Monday, Oct 20th
🕐8am-12pm
📍NOW IN in room 328

Featuring inspiring talks from @rapideRobot, @LingniMa, @danfei_xu, @bowenwen_me and more!

🔗 Check out the full agenda https://t.co/xElFP4cT3N #ICCV2025 #ProjectAria #Meta