Lea Wilken/Müller

One human demonstration. Any multi-fingered hand. Zero-shot sim-to-real visuomotor policy.

morphometricimitation.github.io

Collaborators: @he_siming @ckwolfeofficial @HaozhiQ @LeaMue27 Shankar Sastry, Claire Tomlin, @JitendraMalikCV

Amazon cuts off Muse.

While I am bullish Meta and Muse, I think many people are overlooking the digital knife fight that’s about to occur

Nobody wants to get commoditized or layered here. Let the games begin

1/ today we're rolling out Muse, our new personal ai assistant. Muse is always-on, wicked fast, can use a browser, connect to your apps, and is designed to be secure.

try it now: muse.ai.

DB hard-blocked DelayBahn at 1:35 PM today.

100,000+ people used DelayBahn in the last 7 days, and I guess we finally got noticed 😅

I pushed a workaround and we’re back online, but this will likely happen again.

If you know someone at DB who could help us find a sustainable solution, please DM me.

Would love to work with DB, not around them 🚆❤️

at openai, many people hook their chatgpt up to slack.

people really don't like when a coworker's chatgpt contacts them asking for help with a task, even when they'd be perfectly happy doing that same work if asked by that coworker.

reinforces how much people care about human relationships and helping each other, and want AI to give time back — or enhance time together — rather than become a layer separating people.

This cute little camera robot would also make a great companion.

Beni by Mondo Robotics

Weighs 3.8 lbs (1.7 kg), has a 1.5-hour runtime and a swappable battery. It can track people and capture action videos on the move.

I’ve been capturing 3D human motion for 30 years and today is maybe the biggest day in that history. We are presenting MAMMA at CVPR (oral session 2A). MAMMA is a markerless multi-camera system that has accuracy similar to marker-based systems.

When people share a space, their movements become intertwined. Embodied agents need to understand these social dynamics to interact effectively.

Introducing MAGNet 🧲, a unified autoregressive diffusion forcing model for multi-agent motion generation that captures these interactions.

MAGNet is flexible: predict the future, fill in missing motion, or have people react to each other, all while naturally scaling to N>2 people and generating ultra-long motion sequences.

We wrote a paper: estimating body and hand motion from a pair of glasses! 👓

website: egoallo.github.io
code: github.com/brentyi/egoallo

✮ Pose Priors from Language Models
prosepose.github.io

✮ Synergy and Synchrony in Couple Dances
von31.github.io/synNsync/

Keynote by @LeaMue27

September 29 (12:30 | Suite 2) + hybrid
sites.google.com/andrew.cmu.edu…

(this is our fabulous Social-AI workshop. Don't miss it!)

To what extent does social interaction affect behavior in couples swing dancing?

Our work looks at how we can predict a dancer's next moves based on their past motion alone or by considering both the dancer's and their partner's motions. 🪩🕺🏾 🆚 🪩🕺🏾💃🏾

🧵1/6

7) Prompt: Cinematic style shot of a cotton candy explosion

This generation has some slight morphing, but I love the soldiers running out of the explosion at the end

Our Head of AI @FrederikWarburg wrote about some of our recent AI efforts, if you are interest in spatial 3D intelligence check it out!
📰Blogpost: teton.ai/journal/3d-spa…

If you find this interesting we are expanding the team - teton.ai/company/career

Excited to share some recent work!

"Pose Priors from Language Models"

We show how to use multimodal LMs to improve 3D human pose estimates in situations with physical contact.

Joint work w/ Evonne Ng , @LeaMue27 , Dan Klein (@BerkeleyNLP), @shiryginosar , @trevordarrell