Kfir Goldberg (@kfir99) profile picture

Research @runwayml

Joined June 2011
Photo by Kfir Goldberg (@kfir99)Photo by Kfir Goldberg (@kfir99)Photo by Kfir Goldberg (@kfir99)Photo by Kfir Goldberg (@kfir99)Photo by Kfir Goldberg (@kfir99)Photo by Kfir Goldberg (@kfir99)Photo by Kfir Goldberg (@kfir99)Photo by Kfir Goldberg (@kfir99)Photo by Kfir Goldberg (@kfir99)Photo by Kfir Goldberg (@kfir99)
Happy to share that Inspiration Seeds 🌱 has received a Honorable Mention award at SIGGRAPH 2026! 🎊 We’ve also released all the training and benchmark data used in the paper. Check it out: kfirgoldberg.github.io/Inspi…
Creative work often starts before we can describe what we're looking for. What role can generative models play at this stage? 🌱Our new work, Inspiration Seeds, reveals hidden visual connections between images, creating a purely visual exploration space. 🔗kfirgoldberg.github.io/Inspi…
4
6
2
28
3,117
Every pixel will be generated
Introducing Diffusion-UI. Interactive software where every pixel is generated by a real-time model. Today, we're sharing a new research application that lets generated interfaces use structured data, maintain states and generate controls. Here’s an early look:
1
8
707
Kfir Goldberg retweeted
Praxis-1 dramatically outperforms frontier LLMs on speed and cost. On the same station and tasks, Praxis-1 finished 15.6x faster than GPT-6 Astra driving the arm, at 51x lower cost per completed task.
3
6
7
25
5,487
Praxis-1, our first world action model, is now available for anyone to use. It is currently the leading open-weights robotics model on the RoboLab leaderboard and outperforms every other world action model on the benchmark. More than that, it’s versatile and easy to fine-tune for new hardware and tasks. We’ve tested it on 9 different robot embodiments so far, in simulation and on real hardware with multiple partners, and we’ve seen it reach good performance on a new embodiment with under 30 minutes of demonstrations. Weights, code and fine-tuning recipes are on GitHub and Hugging Face. It can run on a single RTX 5090 with NVFP4. We started our robotics work about a year ago with the thesis that the same video pretraining we do for our creative models can be massively useful for building systems that interact with the physical world, and the benefits of transfer are now becoming clear. When I first talked to people in the field, there was a lot of skepticism about whether video models would be useful in robotics at all, and then about whether you could use them as policies. From first principles, it makes sense that if you can predict the future well in pixels, extracting an action representation should be the easy part. Reality caught up with first principles. One of my favorite things in our technical report is the idea of self-rollouts. Because the model’s performance is bottlenecked by its visual imagination, you can quickly get an intuition for whether it will perform a new task well by rolling out the policy in the model’s imagination. That can speed up evaluation, and it opens a path to doing reinforcement learning in the model’s imagination. There’s been a lot of discussion recently about frontier LLMs being the bitter-pilled way to solve robotics. But scaling performance from unsupervised video is an even better example of the Bitter Lesson than scaling from text. Praxis-1 is more than 10x faster and 50x cheaper than GPT-6 Astra on the manipulation tasks we tested. Frontier LLMs will keep improving rapidly on the Pareto frontier of cost and performance, but so will world models. There are also great ways of combining the strengths of the two. And we are much farther from saturating multimodal data than we are text. Thanks to the mighty Runway Robotics team for making this happen, and to our partners for being so generous with their time helping us test the model across a wide range of hardware and tasks.
Today, we’re making Praxis-1 available to everyone. Our state-of-the-art world action model turns video pretraining into control for real robots, and it ships with open weights under Apache 2.0, ready to run and fine-tune on your own hardware.
8
17
3
95
6,231
🤖 📈
Today, we’re making Praxis-1 available to everyone. Our state-of-the-art world action model turns video pretraining into control for real robots, and it ships with open weights under Apache 2.0, ready to run and fine-tune on your own hardware.
10
398
Kfir Goldberg retweeted
checks calendar doubled ARR again
We crossed $200M ARR last week, doubling from $100M in April. Runway is the world model company. We power the daily work of more than 60 million creators and 95% of the Fortune 100. From award-winning films and ad campaigns to real-time media applications to generalist robotics. Our largest customers are increasingly licensing our frontier models directly. As we expand our research in robotics, the wonderful team from Kinetix, a Paris-based research lab, is joining Runway to help drive our efforts there. Proud of the team for getting us here. Back to building the universal world simulator.
6
17
8
114
31,729
Kfir Goldberg retweeted
Introducing Runway App Studio. Build the creative app you wish existed, just by describing it. It generates images, video and audio with Runway’s models and your Brand Kits, ready for you or your whole team. No code required. See examples in the thread below.
67
61
77
369
204,953
Kfir Goldberg retweeted
Say hello to labs.runway.com A frontier research design studio building prototypes, applications and new media projects with generative video and world models.
7
12
8
167
19,810
Generative Commerce sounds cool 👀
Introducing Generative Commerce. @daletlabs
5
433
Kfir Goldberg retweeted
Agents can now show their reasoning, not just describe it. Visual Thinking is a new research harness that turns an agent's work into real-time video, so every step is visible and easier to follow, check and trust.
31
46
30
803
71,253
simulate the pixels - simulate the world
Runway has been on a tear over the past couple months. Viral HORSE Video contest Solaris: the world's first Interface World Model Praxis-1: open-weight World Action Model for robotics Project Continuum: operating system research application built around real-time interfaces A video model. An interface model. A robotics model. An operating system. Are you getting it? These are not separate pretrains. They’re different applications, built around the same General World Model backbone, with different post-training on top. All of them are examples of what you can do when you can simulate any pixel. So I asked co-CEO Anastasis Germanidis to co-write an essay with me explaining how video, interfaces, operating systems, and robotics all fit together, why video was the right starting point for World Models, where the world is heading if Runway’s bets are right, and whether or not, as someone who simulates worlds, he believes we’re living in a simulation. Welcome to the future. Enjoy! (Video, of course, made with Runway)
1
7
432
Every pixel will be generated
Introducing Project Continuum by Runway Labs, a new operating system research application built around real-time video interfaces. Here's a short demo walktrough:
7
11
4
303
34,306
Kfir Goldberg retweeted
Introducing Project Continuum by @runwayml_labs, a new operating system research application built around real-time video interfaces. Today, we're sharing an early look at four new ways of interacting with your computer: Portals, Visual Thinking, Responsive Video Interfaces and Interactive Worlds. Interface World Models, like Solaris, are reimagining what an interface can be.
38
47
39
450
56,068
Every pixel will be generated
At today's AI Summit, Runway CTO Kamil Sindi shared more on our first World Interface Model, Solaris. A new kind of operating system that builds itself as you interact with it. Every frame is generated in real-time in response to your intention. In his keynote, Kamil shared a clear vision for a future where all software is generated. Without a single line of code. Learn more about Solaris: runway.com/news/research/int…
1
11
962
Kfir Goldberg retweeted
Introducing Praxis-1, an open-weight World Action Model that turns our video pre-training expertise into real world control for robots. Robot demonstration data is limited. But video data is infinite. Praxis-1 extends our bet that the best policy models will learn from video, and use that scale to bring embodied intelligence to every industry. Praxis-1 is built on our large-scale video pre-training and real-time infrastructure, and acts as a policy model for robotics developers and researchers that works across any embodiment or environment, no matter how complex. We are actively testing with early partners including Noble Machines, Standard Bots and Ultra, and will be releasing the weights publicly in the coming months. Learn more and request early access at runway.com/Praxis-1
50
55
42
492
120,367
Kfir Goldberg retweeted
was curious how well claude could make really OOD fancams. questioning what im doing with my life now. schmidhuber fancam
6
17
9
179
60,238
Ex-Muse me?! 🫣
This quoted post is unavailable.
3
125
Kfir Goldberg retweeted
We’ve been experimenting with responsive generative video interfaces. Real-time video models are reshaping responsive design. A thread 🧵
62
151
133
1,372
328,054
Kfir Goldberg retweeted
Honestly can’t wait to play with Runway’s newest models.
7
8
331
46,625
Solaris is wild. Websites are going to be fun again
24
19
2
365
19,884
Kfir Goldberg retweeted
Real-time video models are unlocking new capabilities. A first experiment: a drawing app that animates your sketches as you draw. Under the hood, a video model generates each frame live, turning every idea into motion instantly.
8
39
19
305
56,989