(Pre)training models at @theworldlabs 🌎🧪!! former baulab @ Northeastern, dlab @ EPFL; LAION contributor; I like deep learning & open source.
San Francisco, CA
Joined July 2021
- Tweets1.7K
- Following1K
- Followers1.2K
- Likes8.9K
Pinned Tweet
I am so excited to share what we have been up to!
TLDR; We built Atlas — the best camera conditioned frame autoregressive transformer in the world.
Finally, I can tick training a frontier model off my bucket list :):)
Tysm & shoutout to my incredible team at @theworldlabs
Chris Wendler retweeted
a few space scenes made with atlas. each one started from a single image. atlas generates the video as the camera moves, including the parts of the scene that weren’t in the original image.
orange = input image in 3D space
blue = camera moving through the scene
Chris Wendler retweeted
Atlas beta access has started rolling out!
Here’s a look at how you can control camera paths with pixel-perfect precision.
Chris Wendler retweeted
It's just works, you can also generate a camera path fly through or orbit, and the output is pefect.
Just look at the consistency and details of these renders.
@theworldlabs really solved image to world. This is gonna be huge for so many things.
xitter.cf/LuoErik8lrl/status/210…
It's nuts that with @theworldlabs Atlas, you can just keep generating different angles to generate the whole world from a single starting image.
Image to world with true consistency and control is finally here.
xitter.cf/LuoErik8lrl/status/210…
Atlas beta camera placement is for FPS players +-. @gowthami_s for players that prefer strategy games. Check it out! Simplifies pathing for certain paths and editing of camera paths a lot.
Check out @sheridan_feucht's presentation at #COLM2026.
@sheridan_feucht easily was my favorite presenter during our many lab meetings at @davidbau's lab. Their level of detail is on a completely different level, if you really want to see a neural network taken apart and put back together properly this is where to go.
Chris Wendler retweeted
Most RL techniques in image/video land are very naive, assigning same reward for all the tokens in the trajectory. This is suboptimal and doesn’t really address local artifacts.
We address this with our awesome Local-Global (LoGo) reward, simple idea that works and we tested it on various models and different RL algos (diffusionNFT and GRPO). Once again simple intuition driven ideas work. 🚀
Very excited to share LoGo, my internship project at @theworldlabs on post-training world models! We found that reward design matters a great deal in post-training long-horizon video gen for 3D consistency, echoing what we see in other domains, e.g. LLM reasoning. Check out more 👉 ziqi-ma.github.io/logo-websi…
Chris Wendler retweeted
Small bird, fast wings, Kolibri is here.
78B parameters. 3.46B active. Up to 1M tokens of context. Built in Europe.
Now the weights are yours. Run it on your own hardware, under Apache 2.0.
Chris Wendler retweeted
DynaTokens is going to NeurIPS! Today’s world models are increasingly powerful, but they still struggle with dynamics. We solve this problem by test-time training a few tokens that enable scene dynamics while preserving camera control! More details👉 glab-caltech.github.io/dynat… 🧵below
Chris Wendler retweeted
I don’t normally write these things. But this one hits a bit different. Nearly three years ago I told a16z I wanted to spend part time outside the firm helping @drfeifei start and build a frontier model company. And what followed were some of the most remarkable moments of my career. From being at the founding table. To watching the first git commits. Seeing the very early very rough results that hinted at something much greater. Contributing to the open source. Watching the creation of new model architectures that pushed the state of the art in multiple areas.
I saw the team spin magic from nothing again and again. And I was very privileged to be within the walls. I’m very proud of what was accomplished, and am so excited for what lies ahead.
So congratulations to AMD for entering into an agreement with the leading spatial intelligence frontier lab. And congratulations to the World Labs team on a partner that has the vision, ambition and leadership to be the top AI technology provider globally.
Also congratulations to Dr. Su and Dr. Li. Two world class CEOs with a common vision. The both of you working together is unimaginably legendary. Arguably the smartest leaders in tech with the shared goal of building the world's leading AI capabilities. I know you both share an optimistic view of AIs ability to aid humanity. We need far more of that.
As everyone knows. I’m World Lab’s biggest fan. And will remain so. Thanks to @drfeifei , @BenMildenhall , @jcjohnss and the entire team for letting me tag along. What a crazy fucking ride. You stood at the frontier, and moved it. And will continue to. Again, many congratulations to everyone involved. The future of AI will be so much brighter with this partnership. I can’t wait to see where it leads. Here’s to new worlds!
Chris Wendler retweeted
We are excited to announce that World Labs is joining @AMD.
The research and technical breakthroughs we have achieved since our founding in 2024 have given us a clear vision for AI’s potential to solve problems in the spatial and physical world.
Accelerating the future of spatial and physical intelligence requires scaling our efforts, scaling our reach, and getting closer to the hardware.
Super cool 🧊
Introducing MilliVid, our new method for long-context video generation! MilliVid creates videos that are consistent over long time spans, without using retrieval heuristics or 3D maps! (1/n)
davidcharatan.com/millivid/#
Chris Wendler retweeted
Is university better in the AI age?
I'm seeing:
* Students finish homework, even for just 1 point.
* They want more tests.
* They talk more in class!
* More willing to say "I don't get it!"
* AI explainers are awesome.
Linear algebra, probability, ADAM, Xavier init explainers:
Chris Wendler retweeted
World Tracing is a NeurIPS 2026 Spotlight! 🎉 It’s also our first NeurIPS paper at World Labs. Grateful to everyone who worked on it with me. @jcjohnss @BenMildenhall @_mbanani @KeunhongP @AndyCheng_JH @pzpzpzp1 @Hawaii271828 @chlassner @gengshanY
And there’s more to come: World Tracing Pro, with code and enhanced checkpoints, is on the way 👀
arxiv.org/abs/2606.13652
haoz19.github.io/world-traci…
Chris Wendler retweeted
Block out a world. Let Atlas bring it to life.
A sneak peek at Chisel, now in Atlas beta.
Well said.
Literally brings me tears to hear these words from my hero.
There absolutely is a reason to accelerate. We have cancer that gives you and your loved ones pain.
We have lack of energy, food, and basic medication in half of the population.
We have serious climate / ocean life crisis, economic / political crisis, and other billion problems that needs smart peoples attention.
But most importantly there are not that many smart people. We need more, but we have population crisis on all developed country. And people want to slow down, its all fine, because *they* live in comfort?
Do mathematicians want to better understand universe to ultimately contribute to real world crisis or not?
Chris Wendler retweeted
From 32 input images to real-time flight through @nvidia's Voyager headquarters.
Trained on NVIDIA Blackwell GPUs, Atlas uses these images as 3D spatial context to generate new views, letting you explore with pixel-perfect camera control.
Take a look around.
Chris Wendler retweeted
Atlas beta access is rolling out to users, some ideas for API developers
- give Astra "eyes" in Blender, let it place and render new camera views with Atlas
- 3D reconstruction (this video uses 9 image inputs of my studio to make a scene, any Zillow apartment works)
- graybox-to-world, use depth inputs and generate multi-view renders of a scene
