cindy

research @runwayml prev @stanfordailab

[cindy @cxdwang]

i’m at cvpr in denver this week! if you work on pretraining video/audio foundation models, scaling world models across diverse data and tasks, or joining my team to work on these things at runway, let’s chat—my DMs are open.

[cindy @cxdwang]

only thing more impressive than the technical achievement here is how quickly the team was able to build it and make it run on brand new hardware

[Runway @runwayml]

A breakthrough in real-time video generation.

As a research preview developed with @NVIDIA and shared at @NVIDIAGTC this week, we trained a new real-time video model running on Vera Rubin. HD videos generate instantly, with time-to-first-frame under 100ms. Unlocking an entirely new creative paradigm and bolstering the foundations of our General World Model, GWM-1.

Real-time generation opens a fundamentally different design space for video models and world simulation. We're investing in co-designing our models alongside advances in hardware to keep pushing this frontier.

[cindy @cxdwang]

lots of late nights and massive collaboration across research, eng, product, and creative teams to get this right. really proud of this team and so excited to share what we've been working on!

[Runway @runwayml]

Introducing Image to Video for Gen-4.5, the world's best video model.

Built for longer stories. Precise camera control. Coherent narratives. And characters that stay consistent.

Gen-4.5 Image to Video is available now for all paid plans.

[Joel Kwartler @JoelKwartler]

In 2023 we had the best video generation model in the world, because nobody else had the vision to make video models.

In 2025 we have the best video model in world, because a small team of brilliant creative technologists who care the most about this space is always the winning bet.

More exciting updates still coming in 2025. Because there’s only one Runway, and we’ll always be in a category of our own.

[Runway @runwayml]

Welcome to Research Demo Day 2025. We're sharing a number of exciting announcements towards our mission to build AI systems that simulate the world. https://t.co/8PYXOk8bG2

[cindy @cxdwang]

@j_asminewang 🙋🏻‍♀️

[cindy @cxdwang]

in san diego for neurips dec 1-4! let’s chat about state of the art video models, my DMs are open :)

[Runway @runwayml]

Introducing our new frontier video model, Runway Gen-4.5. Previously known as Whisper Thunder (aka) David.

Gen-4.5 is state-of-the-art and sets a new standard for video generation motion quality, prompt adherence and visual fidelity.

Learn more below.

[Runway @runwayml]

Introducing Runway Aleph, a new way to edit, transform and generate video.

Aleph is a state-of-the-art in-context video model, setting a new frontier for multi-task visual generation, with the ability to perform a wide range of edits on an input video such as adding, removing and transforming objects, getting new angles of a scene and modifying style and lighting, among many other tasks.

[cindy @cxdwang]

welcome to the world, gen-3 alpha ✨

[Runway @runwayml]

Gen-3 Alpha Text to Video is now available to everyone.

A new frontier for high-fidelity, fast and controllable video generation.

Try it now at https://t.co/ekldoIshdw

[Runway @runwayml]

Introducing Gen-3 Alpha: Runway’s new base model for video generation.

Gen-3 Alpha can create highly detailed videos with complex scene changes, a wide range of cinematic choices, and detailed art directions.

https://t.co/YQNE3eqoWf

(1/10)

[rafa @rafaxword]

beyond proud of this one #nytxw

[cindy @cxdwang]

late to this hype but tried it because of @DebAmlen: “If you like word-making games, I highly recommend Wordle, a game its creator, Josh Wardle, a software engineer in Brooklyn, originally designed for his partner.”

[cindy @cxdwang]

@rafaxword king

[cindy @cxdwang]

no better day than today to rep xword swag and catch my lil debut puzzle at https://t.co/iTX6K69VH7!!!

[rafa @rafaxword]

debut from my irl bestie @cxdwang!!! check it out!

[cindy @cxdwang]

@megancguy Thanks Megan! ❤️

[cindy @cxdwang]

Some personal news 🙈

[Sentropy Technologies @sentropy]

We’re thrilled to announce that Sentropy is joining Discord to continue the fight against hate & abuse online! Our missions are deeply complementary & together we can create belonging, safely. Thank you to everyone who supported us on our journey. https://t.co/zlfxD8nw0u

[Sentropy Technologies @sentropy]

We're thrilled to be named to #ForbesAI50 list for our work protecting online communities! Abusive content is everywhere but hard to find. Sentropy’s machine learning models detect harmful content and help platforms proactively remove it. Learn more: https://t.co/qHzClcwyQB