Julia Chen

PhD at ETH Zurich

[Physical Intelligence @physical_int]

Our newest model, π0.7, has some interesting emergent capabilities: it can control a new robot to fold shirts for which we had no shirt folding data, figure out how to use an appliance with language-based coaching, and perform a wide range of dexterous tasks all in one model!

[Julia Chen @juliqchen]

@songyoupeng So inspirational and well deserved 🥹👏🏼

[Danfei Xu @danfei_xu]

EgoVerse enables rigorous science across robots and labs.

We conducted evaluation on real robots across 4 independent academic labs, each with different hardware platforms and system designs.

This enables us to identify durable findings beyond a single robot or lab setup.

[Danfei Xu @danfei_xu]

It was a pleasure to work with you and the rest of the ETH collaborators on EgoVerse. Excited to keep building EgoVerse together!

[Julia Chen @juliqchen]

So stoked to share this new work! And also so grateful to have been able to work with such an amazing team 🤩🤖🦾

[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 🧵

[Simar Kareer @simar_kareer]

We've wanted to study human to robot transfer at scale, but the right dataset was missing. Introducing EgoVerse!

- EgoVerse is about quantity and quality. The data is vast and directly usable
- EgoVerse is growing. We're excited to onboard labs and startups, reach out!

[Jim Fan @DrJimFan]

Teleop is so 2025. Ever since we unveiled EgoScale and the dexterity scaling law, it's been clear to us and the ecosystem that behavior cloning directly from humans is the way to break the curse of teleop. 2026 is all about scaling robot learning without robots.

[Josh @joshavata]

Mecka is excited to power EgoVerse: a growing ecosystem for robot learning from egocentric human data

Proven across 4 leading research labs, EgoVerse data consistently boosts robot performance

We release the tools for anyone to collect data, inference/train, and contribute! 🧵

[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 🧵

[Julia Chen @juliqchen]

coolest sunset I’ve ever seen, iykyk

[dominik helmreich @AmadeusMHH]

Cursor for office work. We just launched Laminize. It´s AI autocomplete for everything. The goal is to go from vibe coding to vibe working.

[Songyou Peng @songyoupeng]

Wanna get a NeRF out just from a casually captured sequence in dynamic real-world scenes? Check out our NeRF On-the-go! #CVPR2024🌟

Project page: https://t.co/IQN2fmiEpU

Amazing work done by Weining Ren (what a great master thesis!)*, @zhuzihan2000*, @juliqchen, and @mapo1

1/

[Russell Wilson @DangeRussWilson]

This Is The Way...

[Marques Brownlee @MKBHD]

Ready for another AirPods Pro giveaway? Got five pairs this time. Just RT and you're in! Giveaway open worldwide, winners will be picked on Monday. Good luck!

[Emoji Mashup Bot 🫡 @EmojiMashupBot]

🥳 partying + 😒 unamused =

[Xander Steenbrugge @xsteenbrugge]

Whoaa, @NvidiaAI's GauGAN web app is super cool!
Play with a conditional GAN right in your browser 😎
https://t.co/IBS1K7Vjdt

[Bill Gates @BillGates]

If you read one article about climate change this week, check out this one from @voxdotcom. Government support for energy R&D is one of the best opportunities to fight climate change. https://t.co/fke57WYxM3

[GTSAM 4.3 @gtsam4]

Just in time for #ICRA2019, we are happy to release GTSAM 4.0 on Github! https://t.co/2oVqBGQO9Q

[Julia Chen @juliqchen]

@FoxNews This isn’t news