Today, we're sharing new research on GWM Worlds 2. Our latest General World Model that generates interactive real-time simulations in continuous 720p video at 24 fps with 48000 Hz audio. Built on top of our foundational audio-visual generation model, GWM Worlds 2 allows you to define the environment, subjects, visual style, physical rules and ambience of any world. Once inside, you steer it with text actions addressed to any subject or to the scene itself, alongside continuous camera motion. The world continues from each new input instead of following a fixed clip or script so sessions have no preset length. GWM Worlds 2 creates a new foundation for interactive entertainment, virtual characters, robotics and embodied-agent simulation. Learn more about GWM Worlds 2 at the link below.

Interfaces that are generated, not coded. Solaris is our first step toward our vision of end-to-end neural software, where user interfaces are streamed directly onto your screen by a real-time video model, without any intermediate code or HTML/CSS. Today we're releasing a technical report and opening it up for limited testing by the community. Amazing work by the team, combining the best of our research in general world models with Runway's HCI spirit.

Today, we're sharing new research on Solaris, our first Interface World Model. Solaris is a new kind of operating system that generates interactive interfaces frame by frame, in real time, with no code. We find that Solaris outperforms frontier LLMs when generating new interfaces, across structural similarity and information retention. Read more and request early access at the link below.

🎬 Video agents can now generate minute-long videos. But can they actually direct? Today, we’re launching 𝐏𝐡𝐲𝐬𝐢𝐨𝐧-𝐀𝐫𝐜 1.0, a new benchmark evaluating complete, multi-scene videos across narrative coherence, cinematic language, and production quality. We tested @runwayml, @LumaLabsAI, @MiniMax_AI, @Kling_ai , @UtopaiStudios and @TapNow_AI on 100 screenplays and 600 generated videos. 🏆 𝐑𝐮𝐧𝐰𝐚𝐲 𝐀𝐠𝐞𝐧𝐭 2.0 𝐫𝐚𝐧𝐤𝐞𝐝 𝐍𝐨. 1 𝐨𝐯𝐞𝐫𝐚𝐥𝐥 𝐚𝐧𝐝 𝐥𝐞𝐝 𝐞𝐯𝐞𝐫𝐲 𝐞𝐯𝐚𝐥𝐮𝐚𝐭𝐢𝐨𝐧 𝐝𝐢𝐦𝐞𝐧𝐬𝐢𝐨𝐧. Its advantage was especially clear across subjective metrics, where cinematic taste matters most. Runway ranked first on all eight. 🔗 Read the full benchmark: lnkd.in/g-5tcwK7

🎥 From still image to speaking character in seconds at Real-Time Live!. 'Runway Characters: Real-Time Expressive AI Characters from a Single Image' turns a single reference image into a fully conversational, expressive AI character. Powered by GWM-1, the system generates real-time lip-sync, facial movement, and head motion at 24fps across both photorealistic and stylized characters. s2026.conference-schedule.or… “Runway Characters: Real-Time Expressive AI Characters from a Single Image” © 2026 Runway, Yining Shi (Runway), Kathleen Lewis (Runway)

Today we're announcing the opening of Runway's first office in France, establishing a new research hub in Paris anchored by an initial team of ten employees. France is one of the world's strongest AI ecosystems. Its concentration of world-class research institutions, the depth of engineering talent coming out of them and the French government's sustained investment in AI infrastructure make it one of the most important places to be building frontier AI. We're hiring in Paris, and across Europe. To learn more and apply for open roles, visit the link below.

This September, the Runway AI Summit is coming to San Francisco. A daylong gathering bringing together industry leaders across robotics, autonomous vehicles, life sciences, infrastructure and more to explore how AI is reshaping the way intelligence interacts with the world. Our inaugural speakers are listed below, with more to be announced soon. Learn more and register at the link below.

One of the most cracked, under the radar research teams is at @runwayml. They were on the OG Stable Diffusion paper and just released the first autoregressive video model. Did a technical deep dive on this + some interesting inference optimizations: amplifypartners.com/blog-pos…

The human mind is no longer the center of AI. Our world is.

You may have recently heard claims that video generation models are "dumb" about physics, and only "world models" (V-JEPA, specifically) have a valid internal model of physics. This turns out to be false. In a recent paper, researchers show that a LINEAR probe of diffusion videogen models predict various "physics" very well, significantly better than V-JEPA or VideoMAE (and plain VAE just sucks). This is noteworthy, because a *linear* probe being this accurate shows that the model has a pretty explicit internal representation of the physics!