Founding Research Scientist @reactorworld. Trying teach machines geometry without telling them about geometry. PhD in weird math from Johns Hopkins.
Joined August 2022
- Tweets103
- Following264
- Followers389
- Likes722
Tommy Mitchel retweeted
How do you tell if authors fabricated their research results? Sometimes: they just tell you. Read, e.g., this caption carefully.
Another banger of a post by my friend Nihar B. Shah on his blog, where he found at least 20+ such #ICLR2027 submissions:
researchonresearch.blog/2026…
Tommy Mitchel retweeted
Introducing NVIDIA Cosmos-3-Nano on Reactor. Two new models, available now via the Reactor API.
• Sim-Bimanual predicts what a robot sees as you move its arms and grippers.
• Sim-Transfer turns simulations into photorealistic video.
Try them now: reactor.inc/cosmos-bimanual
Tommy Mitchel retweeted
Working on Mirror convinced me of something too opinionated for a paper: we've been over-obsessed with "action" in embodied AI. (1/15)
Tommy Mitchel retweeted
At Reactor we ❤️ open-source.
We teamed up with @haoailab to ship an infinite live stream powered by FastVideo’s FastH3:
twitch.tv/dereactor
And we’re open-sourcing everything!
Tommy Mitchel retweeted
oh, thanks for evaluting this for us. We wish we had more compute to distill with more data (like you would have), but it is happy to see that, with our very limited dozens of GPUs, we are already generating good videos.
Also, I hope you could be less mean to us next time, as I believe fastH3 generates sufficient decent videos that many users can already use at much lower cost, definitely not a "random pixel generator"
Speed is easy when you ignore quality. I can generate random pixels under 1 nanosecond and claim to be ♾x faster than H3 and call it H3-ultra-lightning-fast. But this is not how people should innovate on speed in open.
Image and video models are notoriously hard to optimize and we @ fal spend 2-3x more time on evals and making sure optimizations work than actual kernel engineering work.
But when you see people claiming they are X times faster than original while messing the quality to a degree that the outputs has nothing to do with original model, it is annoying.
Numbers below are for this case, but this is not the first/only one doing it. I'd recommend the authors below, and everyone on the field to run their own evals.
Without preference and quality evals in the loop, ai-slop-performance agents can just lead you into a way you generate random pixels and it is just dishonest to call it anything but a random-pixel-generator.
Tommy Mitchel retweeted
We've released the code and checkpoints (policy+WM) for our ECCV2026 work:
Lifting Embodied World Models for Planning and Control
Code: github.com/alexnwang/lifted-…
Checkpoints: huggingface.co/alexnwang/Lif…
What happens to planning and control when world models condition on complex actions?
For example, precisely controlling a human agent may require specifying the motion of each joint.
In this setting, action dimensionality increases, the model becomes difficult to control, and the cost of planning using search-based methods like CEM explodes.
We propose a solution: lift the world model to a higher level of abstraction.
We use a lightweight policy to map high-level waypoint actions → low-level joint sequences, so you can control and plan in a concise space.
Best of all, this is done without finetuning or losing any world model expressiveness.
1/8
Tommy Mitchel retweeted
🚀 Introducing Happy Oyster, the groundbreaking real-time world model from @HappyOysterAI, live today on Reactor!
Explore any world you can imagine, or take the director's chair and shape the story as it happens.
Available via API.
Try it now: reactor.inc/happy-oyster
Tommy Mitchel retweeted
We have some of the best in the real-time video and world model space coming out to our SIGGRAPH event next Monday, July 20th. Come out to meet the team!
luma.com/339enq34
Come on in, the water is warm!
🚀 Introducing Lingbot-World-2, our newest real-time world model.
Richer interactivity, sharper visuals, and advanced camera controls that make exploring what you create feel truly alive.
Available today via API, exclusively on Reactor.
Try it now: reactor.inc/lingbot-world-2
Tommy Mitchel retweeted
🚀 Introducing Lingbot-World-2, our newest real-time world model.
Richer interactivity, sharper visuals, and advanced camera controls that make exploring what you create feel truly alive.
Available today via API, exclusively on Reactor.
Try it now: reactor.inc/lingbot-world-2
Tommy Mitchel retweeted
Come talk about splats 👀 and world models with me today, we @reactorworld are at the @AWSstartups booth at the AWS Summit in LA ✨
Tommy Mitchel retweeted
Can Claude drive a Waymo on @reactorworld?
Yes, but not very well!
Tommy Mitchel retweeted
We have been working closely with the SANA team at @nvidia to make this possible. Real-time 720p world model generation with 6-DoF camera control, live now on Reactor's infrastructure.
🚀 Causal realtime streaming SANA-WM open-sourced!
Thanks to @reactorworld for serving the model — try demo: sana-wm.reactor.inc/
~0.93x realtime on single H100, watch 60s 720p live + 6-DoF camera control.
Code: nvlabs.github.io/Sana/docs/s…
Tommy Mitchel retweeted
Congratulations @vincesitzmann for winning the outstanding Young researcher @CVPR #CVPR2026 PAMI-TC awards!
I’m sure many more awards to come,
Tommy Mitchel retweeted
Watch our CEO and cofounder @taiuti tell the Reactor story, and what we’re doing with world models in this great chat with @nikunj
A Walk In The Park (part II) feat @taiuti 🌎
(00:00) 👋
(01:10) What world models are
(03:42) Origin story from text-to-3D to @reactorworld
(09:22) Deciding to start the company
(11:22) GTA, games, and the path into programming
(15:09) Building in stealth and keeping secrets
(18:32) Picking investors with independent conviction
(21:43) Where world models will grow first
(26:08) Why low latency matters
(29:34) Becoming CEO and scaling the team
(32:23) Final advice
If you're at CVPR, RSVP and come join us tonight at 6:00 PM!
luma.com/qpi7kvmv
Tommy Mitchel retweeted
There have been a lot of fresh discussions lately around "bitter lessons".
Continuing our tradition of community-building at CVPR, our workshop is back! This year's theme: Bitter Lessons in Computer Vision.
Join us on Jun 3rd at 8:45 AM in Room 3A-3D at #CVPR2026
🔗 Website: sites.google.com/view/bitter…
We have an incredible lineup to share their "bitter lessons": Bill Freeman, Alyosha Efros, @georgiagkioxari, @jon_barron, @vincesitzmann, @BharathHarihar3, @ShenlongWang, David Forsyth, @dimadamen @ev4n3sce, @CVPR
This place is a blast! Come join us, we're hiring!
Today Reactor is coming out of stealth. We’ve raised $59M in Seed and Series A funding, led by @lightspeedvp, with participation from @AmplifyPartners, @wndrco, @Sky9Capital, and @FPVventures.
Reactor is the platform for building in the World Model era: the infrastructure that lets developers build with them at global scale for the first time. Stream from a frontier World Model to your app, in real time, all in under 10 lines of code.
World Models represent the next major shift in AI: pixels, audio and actions are generated on the fly, in real-time, in response to user inputs, and to the environment. Every time computing has made a shift from passive to interactive, entire industries appeared that didn't exist before. We're standing in front of such moment again.
Over the last 6 months, we’ve assembled an all-star team with alumni from Apple, Meta, Google, Luma AI, Netflix, and Replicate. We're already partnering with some of the biggest names and labs in the world, and hundreds of developers are already building on Reactor.
The World Model era starts now.