AI agents can now reliably review a patient's chart -- but agentic access needs data + workflows beyond USCDI FHIR APIs. Under current rules, a practice can spend months navigating EHR partner fees, IP terms, and app registration. There's a better way... https://t.co/IlhgHpgLpU
Spent the past few weeks building a fully automated pipeline for egocentric manipulation data with @KyleHeJiang.
Any new manipulation task captured using our own wearable sensing platform can now be dropped into the same pipeline with minimal manual fix.
Instead of raw videos and annotations, we transform human demonstrations into robot-ready training data.
Next, we're bringing touch into the loop with tactile gloves.
EXCLUSIVE: We uncovered a secret corporate scheme to raise grocery prices.
We found that Instacart is using AI algorithms to charge customers different prices for the same items.
The scary part? It's not just online. It's in physical grocery stores too.
Our months-long investigation with @ConsumerReports and @Groundwork found it could cost families $1200/year.
A new open-source physics engine just dropped… and it could change how robots learn.
Newton, built by @nvidia with support from @GoogleDeepMind and Disney Research, is now part of The Linux Foundation. It’s designed to bring precise, GPU-powered physics to robotics and simulation research.
Why it stands out:
✅ Runs entirely on the GPU for faster, richer simulations
✅ Open and modular, so you can plug in your own solvers or use it for differentiable physics
✅ Works with OpenUSD, Isaac Lab, and MuJoCo Warp
✅ Fully open-source under the Linux Foundation
Another simulator? It’s a shared foundation for faster iteration and more realistic training before deploying in the real world.
🔗 Docs: https://t.co/RcbaWz6V2A
🔗 NVIDIA announcement: https://t.co/BPwJipuNym
—-
Weekly robotics and AI insights.
Subscribe free: https://t.co/dsa6wcvq6n
We pray for mindfulness of all the blessings of this life: for the beauty of the earth, for loving relationships and nurturing community, for meaningful work, for passion, creativity, and play. May our lives be an offering of gratitude and a response to Love.
May our lives be the answer to the prayers we offer. ⛪
Most datasets for hand object manipulation are slow to build, expensive to capture, or too small to be useful… not this:
HO Cap feels different. A simple idea done well.
They built an 8 camera RealSense setup with an Azure Kinect on top.
Users wear a HoloLens so they also get a first person view.
Everything is calibrated so the output is consistent.
The pipeline is semi automatic:
•BundleSDF reconstructs the object mesh
•FoundationPose gives the initial object pose
•MediaPipe gives the hand pose
•A joint SDF based optimization cleans everything up
The result is 64 objects and 64 videos with clean poses, masks, and first person data.
No expensive mocap rigs. No custom gloves. No full manual labeling.
The rough edges are clear. Some objects do not reconstruct well. MediaPipe sometimes drops joints. Small objects can break the pose estimation. Failed videos are removed.
But the direction matters.
This type of data is what dexterous robot learning needs right now.
These actions are still very hard for current systems.
Thanks for sharing, @YuXiang_IRVL!!!
Project page:
https://t.co/n3QgjGw0Q7
Dataset toolbox:
https://t.co/NwXmVk8OlP
—-
Weekly robotics and AI insights.
Subscribe free: https://t.co/dsa6wcvq6n
A predictive model for the treatment outcomes of patients with secondary mitral regurgitation based on machine learning and model interpretation
https://t.co/w6ldj1BLD1
Inspired by @TaliaRinger, powered by @NanoBanana:
Create a detailed poster of the English Alphabet, with each letter shown in capital and lowercase form, with a visual to remember it. The infographic should be ideal for toddlers to learn the alphabet, and should be Star Wars themed.
It could have been Indianised a bit more, but loving how vibrant these turned out - the colourful borders, the umbrella, the fish with lotus flowers, and that switch from “Van” to “Auto” 😄
Same prompt as original tweet, just made it "Indian-Themed"
Nano Banana Pro is wild.
Here’s my favorite use case so far: take papers or really long articles and turn them into a detailed whiteboard photo.
It’s basically the greatest compression algorithm in human history.
Today is Nano Banana Pro day. It is already live for me in the Gemini app and on the web. I'll keep announcements and reactions in this thread. It's very fun to use, and you can see reasoning traces during a generation. Things should kick off officially soon.
Video from the coast of British Columbia may be the first documented instance of a wild wolf using a tool, according to the researchers who published it on Monday. https://t.co/ShTQj2REsc
“I think all the attention, all the focus, all the money, is concentrated into this idea that you can build one model through a bunch of compute and that is going to solve all problems for all companies and all people,” @ClementDelangue. “I think the reality is that you’ll see in the next few months, next few years, kind of like a multiplicity of models that are more customized, specialized, that are going to solve different problems.” 💯✨
Sunday Robotics has a new way to train robots to do common household tasks. The startup plans to put its fully autonomous robots in homes next year. https://t.co/QcnaIRKVWO