Zhumazhan Balapanov
177 posts
Zhumazhan Balapanov
@ZBalapanov
founding engineer @reactorworld | founder @ Astyk (acquired) | previously - neurips,iaseai
Присоединился Mayıs 2022
86 Подписки103 Подписчики
Huge personal update: I moved 5800 miles away from home to join @mirendil
We're building towards what I think is the most exciting and impactful use of the models: accelerating scientific research.
A wonderfully bright future lies ahead if we get this right :)
English
What if Maradona never scored with his hand in 1986?
We regenerated that moment with a world model and let history play out differently.
By @eliott__mogenet
English
Excited for this to go live! @Snapchat is cooked. Try now at sana-streaming.reactor.inc
reactor@reactorworld
Real-time video editing is here. SANA-Streaming by @NVIDIA is now live on Reactor. Change the style, the scene, the mood of any video as it plays, with no rendering wait. Try it now: sana-streaming.reactor.inc
English
Real-time video editing is here.
SANA-Streaming by @NVIDIA is now live on Reactor. Change the style, the scene, the mood of any video as it plays, with no rendering wait.
Try it now: sana-streaming.reactor.inc
English
GIF
QME
The models are getting there @robbyant_brain. The infra is getting there @reactorworld. But capability alone won't make a video world model people love — the missing piece is fun.
That's what a gamification layer solves! @hugothomel 's insightful blog answers the question: how do you make world models people actually enjoy using?
Must-read if you'd like to build entertainment experiences on interactive video. And exactly why I believe in Reactor — once this is a few-lines-of-code service, the cool stuff is inevitable.🥳
hugo@hugothomel
English
Crazy Taxi, but Waymo, running on @reactorworld.
So clearly easy-to-run world models are going to start diffusing into more games/experiences/etc.
Conner Ruhl@connerruhl
Can Claude drive a Waymo on @reactorworld? Yes, but not very well!
English
New blog post: The Forgetting Wall in Video and World Models
Long-horizon video generation is not just limited by compute. It is limited by how much of its own past the model can afford to remember.
I wrote about why long videos drift, why KV cache becomes the memory bottleneck, and why compression is a key direction for future video/world models.
haochengxi.github.io/posts/forgetti…
English
🚀 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/sana…
Enze Xie@xieenze_jr
Please check our SANA-WM, an efficient minute-scale world model with hybrid linear attention! 🎉
English
If you want to learn more about @reactorworld and world models, watch this.
Nikunj Kothari@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
English
Proud of what the team has shipped here!
Myself and other members of the Reactor team will be at CVPR - come try LongLive 2.0 and a bunch of other models out in person!
And if democratizing world models and interactive media access is something that excites you, DM us. We're always looking to connect with people who care about this !
reactor@reactorworld
Introducing LongLive 2.0 by @NVIDIA. Real-time text-to-video with full multi-shot control. Build your story shot by shot, scene by scene. Available now on Reactor.
English
Super excited to share that we, Morpheus AI, come out of stealth today and are joining @Roblox.
It was an incredible honor to join Xun as founding member, grow the team, and witness our achievements in all the months that followed.
As next steps, we will continue building our foundational video world models. I’m personally excited most about optimizing everything optimizable!
Xun Huang@xxunhuang
I'm excited to announce that the Morpheus AI team is joining Roblox! Over the past two years, I’ve focused on developing the foundational architectures behind modern video world models, including Self Forcing and AR-DiT. This work unlocked something unprecedented: the ability to move beyond offline, pre-rendered AI video generation and instead simulate interactive worlds in real time. Realizing the massive potential of this technology is what drove me to found Morpheus in August 2025. In the months since, our incredible team has pushed those boundaries further than we ever thought possible. We've always believed video world models will reshape how games are created. Roblox Reality is an ambitious bet on that exact future, and it lines up perfectly with what we set out to do: bridging the gap between deterministic game engines and generative world models. Joining Roblox means our technology will help power experiences that reach millions of players every day. To our team, to @a16z and other investors, and to the advisors, partners, and supporters who believed in this from the very beginning — thank you. We're just getting started. Excited to build this at scale.
English
Time to 𝗿𝗲-𝗺𝗲𝗲𝘁 𝗟𝗶𝗻𝗴𝗯𝗼𝘁-𝗪𝗼𝗿𝗹𝗱-fast — powered by @reactorworld 🌍!
Lingbot is one of the most powerful open-source world models in the community, from the Robbyant Team.
We got it running in real-time — and, just as importantly, made it genuinely fun and easy to use.
🔗 github.com/Robbyant/lingb…
English
This place is a blast! Come join us, we're hiring!
reactor@reactorworld
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.
English
As models become faster and real-time, a completely new modality takes shape.
A modality where you are not just a spectator of what generates, but instead an active agent.
Reactor is here to drive this new future and shape the tools that allow this new form of interaction.
Excited to be part of this, and so proud of all the goals the team has achieved leading up to this 🧡
reactor@reactorworld
Today, we’re coming out of stealth with $59M in seed and Series A funding, led by Lightspeed, with Amplify Partners, WndrCo, Sky9, FPV, and incredible angels. For a long time, pixels have been pre-rendered and played back passively. World Models change that entirely: pixels are generated on the fly, in real time, in response to what you're doing. 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. Reactor is the platform for building in the World Model era: the infrastructure that lets any developer build with World Models at global scale. With only a few lines of code, and you're streaming pixels from a frontier World Model into your product, in real time, at massively. Over the last 6 months, we’ve assembled an all-star team from Apple, Meta, Google, Luma AI, Netflix, and Replicate. We're already partnering with some of the biggest companies in the world, and hundreds of developers are already building on Reactor today.
English
It’s time to unveil what we’ve been working on: today, @reactorworld comes out of stealth with $59M to power the World Model era.
And we’re just getting started.
reactor@reactorworld
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.
English