Sabitlenmiş Tweet
Towards Universal Simulation
agermanidis.com/writings/unive…
English
Anastasis Germanidis
559 posts
Anastasis Germanidis
@agermanidis
Simple ideas, pursued maximally. Co-Founder & Co-CEO @runwayml.
New York, NY Katılım Mayıs 2011
456 Takip Edilen5.5K Takipçiler
Anastasis Germanidis retweetledi
Simulating everything, sort of: The promise and limits of world models arstechnica.com/ai/2026/07/sim…
English
Runway Agent 2.0 ranks #1 on Physion-Arc 1.0, a new benchmark for minute-long, multi-shot video generation, leading across every dimension
Physion Labs Official@Physion_Labs
🎬 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
English
Real-World Superintelligence
I wrote short essay on how to build AI systems that can take the right actions in an unpredictable world.
agermanidis.com/writings/real-…
English
Anastasis Germanidis retweetledi
Excited to demo Runway Characters at SIGGRAPH with @yining_shi !
ACM SIGGRAPH@siggraph
🎥 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.org/presentation/?… “Runway Characters: Real-Time Expressive AI Characters from a Single Image” © 2026 Runway, Yining Shi (Runway), Kathleen Lewis (Runway)
English
Announcing our new research hub in Sentier, Paris - advancing world models for robotics and deepening our partnerships with physical AI companies across Europe.
Runway@runwayml
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.
English
Anastasis Germanidis retweetledi
As a follow-up to our Kueue post on sharing idle research compute, we wrote up how we reallocate GPUs from production to research overnight, using queueing theory to know just how many we can spare. More research FLOPs and shorter queue waits: runwayml.com/news/borrowing…
English
Announcing our first summit dedicated to world models, coming to SF this September.
Very excited to have some incredible researchers, founders, and thinkers join us on stage to talk about the biggest challenges in real-time video generation, robotics foundation models, more.
Runway@runwayml
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.
English
Anastasis Germanidis retweetledi
Introducing Agent 2.0
Go from a simple prompt to fully realized marketing briefs and campaign assets right inside of Runway Agent. You can also easily analyze your performance data to improve your creative and scale it across platforms, formats and markets.
Agent is being built to become the most capable autonomous agent for real-world work.
English
@poolio Congrats on a great run & good luck on what's next!
English
After 15 years (4 internships and exactly 8 years full-time), today is my last day at Google. Growing up as a scientist at Brain and DeepMind was an incredible privilege, and I'm so thankful for the people who made it such a special place. I went from editing decision trees by hand as an intern, to exploring representation learning, latent-variable models, and diffusion as an AI researcher, to kicking off a new wave in generative 3D with DreamFusion, to scaling up generative models with Veo, Genie, and Omni. We're just beginning to build systems that can understand and simulate the real world, and I'm excited to see what’s next 🧠🐸🚀
English
Great writeup on how we deploy real-time autoregressive diffusion models at scale.
sisyphus bar and grill@itunpredictable
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-posts/the…
English
AI is quickly moving beyond emulating the human mind to predicting an increasingly large percentage of all observations in the world. General world models will become a new foundational infrastructure for humanity. A short video essay on the path ahead.
Runway@runwayml
The human mind is no longer the center of AI. Our world is.
English
@agermanidis Hey Anastasis. I'd love to hear more about using your real-time models for AI avatars. I'm working on exactly that rn for an immersive experience. Got a link to the BBC case study or a link to other info?
English
This May, Runway added more ARR than in all of 2025 combined.
I spent the past few days visiting some of our largest customers in Europe. Enterprises across the region are rebuilding their workflows around generative video.
The BBC used our real-time models to bring live AI avatars to broadcast TV. Salomon built their latest global campaign on Runway. The bottleneck is increasingly moving from production to direction.
We started Runway when visual generative models were in their infancy, and it still feels so early.
English
Today we’re announcing London as Runway’s European HQ, and doubling down on our investment in the UK AI ecosystem.
In under two years, our London team has become central to our research, including foundational work on GWM-1, our latest general world model. The caliber of talent and industry presence here makes it an ideal environment for the next chapter of Runway’s growth and for shaping the next generation of AI with world simulation.
I’ll be in London for the week; DM me if you want to meet up!
Seb Johnson@SebJohnsonUK
ANOTHER big AI Lab is massively investing in London. This time it is @runwayml - the Nvidia backed world world provider. It has just announced plans to make London its new European headquarters and will invest more than $200 million into the U.K. @KanishkaNarayan, the minister of AI, said: "Runway’s new London hub will bring pioneering research into world models to the UK, helping power breakthroughs across industries from film and gaming to science and robotics,” “We want the world’s most ambitious AI firms to build their future here, and that is exactly what Runway is doing.” Google, Anthropic, OpenAI have all announced plans to expand in London which is quickly becoming Europe's AI hub. LETS GO
English
Anastasis Germanidis retweetledi
Anastasis Germanidis retweetledi
Introducing Runway MCP. Now you can connect Runway directly into Claude, ChatGPT, Cursor, Replit and more.
Generate polished images and videos with state-of-the-art models, like Gen-4.5, Seedance 2.0, GPT Images 2.0, Kling and more. Right from where you're already working.
Connect the MCP to your agent in seconds at the link below.
English
@fabianstelzer @andymac3d @runwayml Would love to help onboard you. API very much a priority! DMs open
English
@agermanidis @andymac3d @runwayml happy to be corrected! Would love to use Runway models more via API. Last time I tried it didn’t seem like a priority vs inference in your own stack
English
Not so fast Google Omni - @runwayml is back in the game with Aleph 2.0. Make changes and edits to videos (up to 30s) via prompts, references or restyle a frame with your favourite image editor (NB Pro or GPT Image 2.0). You can even prompt additional motion on top of your edits. Great stuff!
p.s. This is simple tests restyling the original Seedream 2.0 video with Aleph 2.0 using a restyled frame with NanoBanana and a simple split screen. Couldn't see any misalignment / offsets - really cool.
Will do some more testing! 😎
English
English
@andymac3d @runwayml Runway doesn’t have enough GPUs to offer these via an API properly alas
this has always been a huge blocker for their models’ adoption
English