Karan Desai (KD)

Building @theworldlabs, prev: PhD @UMichCSE.
I fight the devil in the details 🧐

[Karan Desai (KD) @kdexd]

We cooked something new at @theworldlabs! I am so excited to share our first product with everyone! Create, edit, and export large and persistent worlds now, signup at https://t.co/uG2xItNNuD

[World Labs @theworldlabs]

Introducing Marble by World Labs: a foundation for a spatially intelligent future.

Create your world at https://t.co/V267VJu1H9

[World Labs @theworldlabs]

60 million Gaussian splats. One massive dark fantasy world ready to explore! ⚔️

Created entirely with Marble, this persistent world is brought to life in-browser via our Spark 2.0 LoD system and Three.js

Fly through it yourself and learn more about how it was made 👇

[World Labs @theworldlabs]

We're excited to be rolling out two model updates today!

Marble 1.1: Improves lighting and contrast, with a major reduction in visual artifacts.

Marble 1.1-Plus: Our new model built for scale. Create larger, more complex environments than ever before.

[World Labs @theworldlabs]

Big congrats to the Open Art team on their new launch. Powered by the World Labs API. 🌎

[Karan Desai (KD) @kdexd]

It's time to keep building and marching forward 🙏

[World Labs @theworldlabs]

World Labs has raised $1 billion in new funding. We are grateful and excited to partner with our investors, including AMD, Autodesk, Emerson Collective, Fidelity Management & Research Company, NVIDIA, and Sea, among others.

https://t.co/MfK7mLGKPH

[Karan Desai (KD) @kdexd]

My friend @KeunhongP asked me to buy a domain of my name before he buys it first and hoards it forever, so now my personal webpage is https://t.co/OvbKYqf2aq -- glad this domain was still available 😀

[Jay Karhade @JayKarhade]

Introducing Any4D, a unified transformer for fully feed-forward, dense, metric-scale 4D reconstruction from flexible inputs!

Any4D regresses per-pixel motion + geometry across frames in one pass — 15× faster, 2–3× more accurate reconstructions ⚡📈

Details + code below 👇

Exciting collab with @Nik__V__ @YuchenZhan54250 Tanisha Gupta @akashshrm02 @smash0190 @RamananDeva

[Karan Desai (KD) @kdexd]

We cooked some Real Time Frame Models at @theworldlabs! Try them out :)

[World Labs @theworldlabs]

Introducing RTFM (Real-Time Frame Model): a highly efficient World Model that generates video frames in real time as you interact with it, powered by a single H100 GPU.

RTFM renders persistent and 3D consistent worlds, both real and imaginary.

Try our demo of RTFM today!

[Karan Desai (KD) @kdexd]

Take a look at what we've been cooking at @theworldlabs — expansive, aesthetic, and consistent 3D worlds from just one image! Checkout our blog: https://t.co/DVOV53fX8j 🌎
Join https://t.co/qCIhkOvWkI to try out the model yourself!

[World Labs @theworldlabs]

Generate persistent 3D worlds from a single image, bigger and better than ever!

We’re excited to share our latest results and invite you to try out our world generation model in a limited beta preview.

[spark @sparkjsdev]

Open Sourcing Forge: 3D Gaussian splat rendering for web developers!

3DGS has become a dominant paradigm for differentiable rendering, combining high visual quality and real-time rendering. However, support for splatting on the web still lags behind its adoption in AI.

[Karan Desai (KD) @kdexd]

@KLM Had an absolutely horrible experience today, SFO - AMS - BOM. First flight got delayed, second rebooked via LHR, that got cancelled, finally rebooked via Emirates. Total delay = 10 hours. I lost my comfort plus seat booking. Have some accountability, at least offer a refund or upgrade.

[Dhruv Batra @DhruvBatra_]

Here’s what we’ve been training — a team of AI agents that take actions on the web.

[Karan Desai (KD) @kdexd]

@deviparikh Yay! Love this sneak peek! Congratulations @yutori_ai team, I am rooting for you :-)

[Devi Parikh @deviparikh]

Excited to share a sneak peek into what we've been building at Yutori!

What you see below is our trained model and internal prototype — multiple agents running in parallel in the background, completing tasks of varying complexity, relevant information and cues to step in being surfaced to the user.

More examples 👇

This is barely scratching the surface of what agents can do for you day-to-day.

Follow along at @yutori_ai — more to come soon!

[Karan Desai (KD) @kdexd]

@DrJimFan @FelixHill84 This blog is a very painful and sobering read. Rest in peace, Felix.
For a thoughtful reader, I recommend one of my favorite CVPR papers of all time — "The Affective Growth of Computer Vision". https://t.co/Z4JwoK6Eoy

[World Labs @theworldlabs]

Happy Holidays to everyone across all worlds!

[Karan Desai (KD) @kdexd]

Very cool workflow with scenes generated by our @theworldlabs model! 🚀

[Lovis Odin @OdinLovis]

More coming soon ! I manage to integrate for the first time volumetric 3D video made with @kartel_ai inside the AI world generated in gaussian splatting by @theworldlabs !!
I coded all in three.js! And it's possible to integrate elements on the fly ;)
And so you can imagine soon what we will produce with that en AI : consistency of character and environment, relighting etc...

[Karan Desai (KD) @kdexd]

Open in YouTube mobile app, this is so much fun lol

[World Labs @theworldlabs]

360 world tour 🌐

https://t.co/z7EFjyeHup

[Karan Desai (KD) @kdexd]

@dangengdg Oh hello @SarahJabbour_

[Daniel Geng @dangengdg]

What happens when you train a video generation model to be conditioned on motion?

Turns out you can perform "motion prompting," just like you might prompt an LLM! Doing so enables many different capabilities. Here’s a few examples – check out this thread 🧵 for more results!