Karan Desai (KD)

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 marble.worldlabs.ai

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.

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

It's time to keep building and marching forward 🙏

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 karandes.ai -- glad this domain was still available 😀

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

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

Take a look at what we've been cooking at @theworldlabs — expansive, aesthetic, and consistent 3D worlds from just one image! Checkout our blog: worldlabs.ai/blog/bigger-be… 🌎 Join worldlabs.ai/waitlist to try out the model yourself!

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.

@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.

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

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

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!

@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". openaccess.thecvf.com/content/CVPR20…

This is the most gut-wrenching blog I've read, because it's so real and so close to heart. The author is no longer with us. I'm in tears. AI is not supposed to be 200B weights of stress and pain. It used to be a place of coffee-infused eureka moments, of exciting late-night arxiv safaris, of wicked smart ideas that put smile on our faces. But all the incoming capital and attention seem to be forcing everyone to race to the bottom. Jensen always tells us not to use phrases like "beat this, crush that". I absolutely love this perspective. We are here to lift up an entire ecosystem, not to send anyone to oblivion. I like to think of my work as expanding the pie. We need to bake the pie first, together, the bigger the better, before dividing it. It gives me comfort knowing that our team's works moved the needle for robotics, even just by a tiny bit. AI is not a zero sum game. In fact, it is perhaps the most positive-sum game that humanity ever plays. And we as a community should act this way. Take care of each other. Send love to "competitors" - because in the grand schemes of things, we are all coauthors of an accelerated future. I never had the privilege to know Felix irl, but I loved his research taste and set up Google Scholar alert for every one of his new papers. His works in agents and VLMs had a big influence on mine. He would've been a great friend. I want to get to know him, but I couldn't any more. RIP Felix. May the next world have no wars to fight.

Happy Holidays to everyone across all worlds!

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

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

@dangengdg Oh hello @SarahJabbour_

First, we train a video model to take a first frame, text, and **point trajectories** — a super flexible representation of motion. We then construct **motion prompts** to feed to the model. For example, a really simple motion prompt allows a user to “interact” with an image.

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!

Want to push the limits of where this tech can go and build the products that put it into users' hands? Join us! jobs.ashbyhq.com/worldlabs