Vibhaa Sivaraman

ML Researcher (PhD from @mitcsail) interested in LLM agents and lately world models @theworldlabs. Bharatanatyam dancer & @PrincetonCS’ 2017. Pronouns: she/her

[Karan Desai (KD) @kdexd]

We cooked a new model at @theworldlabs! Atlas, our next-generation world model, is out today and I am so excited to finally talk about this one! 🔥🌍

The main idea and unique feature of Atlas is camera-conditioned sparse frame generation: give it a one or more images and the exact camera poses you want, and it generates frames at those poses, consistent in 3D with everything it has seen. You can do also many things with this model, like
(1) Sparse reconstruction: even 2-3 photos of an apartment or warehouse are enough for making a "digital twin".
(2) Keyframing for film-making: place a handful of frames in 3D space and direct a 1 minute video at 1440p through them. You can frame every shot yourself instead of pulling the lever of a slot machine.
(3) Bullet time (my favorite!): You can freeze the time mid confetti explosion and fly the camera through it, from footage of 3-5 cell phones on tripods. The Matrix needed a warehouse of cameras for that shot, now it fits in a backpack.

Because every task is just a sequence of frames + cameras, we trained Atlas on a big mix of tasks and data. I personally drew a lot of satisfaction in pouring SO MUCH DATA into this big boy. Due to task generality, Atlas can also do text-to-image, 360 panoramic generation, outpainting, depth estimation, etc. Only my teammates know how many bernese mountain dogs I have generated with this model in text-to-image mode. XD

A huge shoutout to the entire team at World Labs, I feel so lucky to work with such talented people and have made long-lasting friendships being in the trenches together, day in and day out - @KeunhongP @_mbanani @BhamidipatiPan1 @_nikunj_gupta @gowthami_s @rmgarg02 @vibhaa14 @wendlerch @hyl0m0rphism @DrTunnels @bardienus and many more (not all are on X).

Blog: https://t.co/K1UUtlTB4Z
See thread below for details 🧵⬇️

[Keunhong Park @KeunhongP]

Atlas is live! A spatial foundation model, trained in-house from scratch.

After shipping RTFM last year, I was convinced a single camera-conditioned model could unify most spatial generation tasks. Atlas is that bet at scale.

The core idea👇

[Vibhaa Sivaraman @vibhaa14]

The camera-control precision of this model is insane! Has been an incredible privilege to work on this model with this great team!

[World Labs @theworldlabs]

Introducing Atlas:

The world's first multimodal world model that generates image and video frames with pixel-perfect camera control and reconstructs them in 3D.

Model the world, move the camera, and simulate space & time.

[Fei-Fei Li @drfeifei]

https://t.co/Kt50ttQRMJ

[spark @sparkjsdev]

Spark 2.0 is here! 🚀

We’re redefining what’s possible on the web with a streamable LoD system for 3D Gaussian Splatting.

Built on Three.js, you can now stream massive 100M+ splat worlds to any device from mobile to VR using WebGL2. All open-source.

Dive into the tech 👇

[Ben Mildenhall @BenMildenhall]

see around corners with Marble 1.1 Plus 👀

[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]

Text became the universal interface for software.

3D is becoming the universal interface for space.

It’s the medium that lets humans and AI generate, edit, simulate, and share worlds together.

https://t.co/hd0PMNTv6j

[World Labs @theworldlabs]

We’re building foundational world models to power the next era of 3D. From robotics to gaming, spatial intelligence unlocks entirely new worlds.

Powered by inference at scale – shoutout to Baseten.

[World Labs @theworldlabs]

We’re hosting our first-ever hackathon next Friday in SF.
Come build at the frontier of spatial intelligence.
Apply below ↓

[Amazon Web Services @awscloud]

Automate browser tasks with frontier-class agents.

Amazon Nova Act lets developers build AI agents that automate UI workflows reliably at scale. Turn complex processes into smooth operations in hours, not weeks.

[Amazon Science @AmazonScience]

Nova Act is now⚡️ enterprise ready ⚡️ and we've added new capabilities to our preview to help you take your prototype to production—with 90%+ reliability across our early enterprise customer use cases!

[Amazon Science @AmazonScience]

Meet Amazon Nova Act — an effortless way to build AI agents that can reliably use browsers 🧑‍💻

With our new model, compose robust steps into complex workflows; handle everything from bookings to QA testing. Getting started takes just 3 lines of code.

See what Nova Act can do 🧵👇

[Amazon Science @AmazonScience]

Thanks for all the interest in Amazon Nova Act! If you requested to sign up, you can visit https://t.co/ijXtM4K7Ej to create your API key. We're excited to see what you build and hear your feedback.

[Vibhaa Sivaraman @vibhaa14]

@AmazonScience Incredibly excited for this and proud to be a part of this team!

[Jennifer Rexford @jrexnet]

Awesome connecting with @vibhaa14 at #PrincetonReunions!

[Vibhaa Sivaraman @vibhaa14]

@HariBalakrish20 @MassRMV If you try first thing tomorrow morning, you'll likely see slots for the day after the last day currently shown. That's how I got my appointment. My guess is that they release slots at a fixed time every (workday?) morning.

[Vibhaa Sivaraman @vibhaa14]

@MArashloo Congratulations!!

[Vibhaa Sivaraman @vibhaa14]

@justinesherry @EberlyCMU Only recently learned that MIT has a set of teaching workshops for grad students aimed at this, but so few students even know.
https://t.co/1MsfWfdXtg