Katie Lewis Grumman

192 posts

Katie Lewis Grumman banner
Katie Lewis Grumman

Katie Lewis Grumman

@KatieLewisMIT

Research @runwayml , previously PhD @MIT_CSAIL Computer vision, generative & creative AI research. Opinions are my own.

Katılım Aralık 2018
384 Takip Edilen1.2K Takipçiler
Katie Lewis Grumman retweetledi
Yining Shi
Yining Shi@yining_shi·
@KatieLewisMIT and I are doing a live demo for Runway characters on SIGGRAPH Real-time Live! We will create a real-time video character from scratch on the stage! Please come by and check it out if you are at SIGGRAPH this year.
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
0
4
16
1.3K
Katie Lewis Grumman retweetledi
Kamil Sindi
Kamil Sindi@kamilsindi·
We open-sourced AVTensor, the Rust media decoder behind Runway's training pipelines. It decodes video and audio on one timeline straight into PyTorch tensors, with decode-time resize up to 6× faster than PyTorch's torchcodec. It improved our training MFU by 1.8pp. Check it out! runwayml.com/news/avtensor-…
English
2
16
64
13.3K
Katie Lewis Grumman
Katie Lewis Grumman@KatieLewisMIT·
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
0
3
22
1.5K
Katie Lewis Grumman retweetledi
ACM SIGGRAPH
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)
ACM SIGGRAPH tweet media
English
2
7
42
11.4K
Katie Lewis Grumman retweetledi
Camille Ricketts
Camille Ricketts@camillericketts·
Got to hang with the @runwayml folks during their film festival week, and pull back the curtain in today's early days ☀️ As a movie buff, I was both so thrilled to be invited in, and prepared to have complex feelings about it. What I found was a very rare culture - wisdom for AI startups looking to build something with a beating heart, a clear haven for artists, a team rallying to take on a wide world beyond video.
English
2
9
36
9.8K
Katie Lewis Grumman
Katie Lewis Grumman@KatieLewisMIT·
🤖Runway Robotics: “A complete toolkit for robot learning. From policy inference and evaluation to synthetic data generation, every component is powered by GWM-1, our state-of-the-art General World Model. Pick the surface you need — we'll work with you to fit it to your hardware.” runwayml.com/product/roboti…
English
0
0
1
131
Katie Lewis Grumman
Katie Lewis Grumman@KatieLewisMIT·
I’m at CVPR through Sunday. DM me if you want to grab a coffee! I lead a research team at Runway and am excited to chat with folks about our research on general world models, real-time video generation, and creative tools. Links to our recent research and open roles in thread
English
6
1
53
4.6K
Katie Lewis Grumman
Katie Lewis Grumman@KatieLewisMIT·
We’re hiring across many roles in research and engineering! We’re a remote-first company, with opportunities to work in person at our HQ in New York or offices in SF, Seattle, London, and Tel Aviv! jobs.ashbyhq.com/runway-ml?depa…
English
1
0
2
503
Katie Lewis Grumman
Katie Lewis Grumman@KatieLewisMIT·
Real-time interactive video generation for explorable environments and physical AI: x.com/runwayml/statu… runwayml.com/research/how-r…
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.

English
0
0
0
431
Katie Lewis Grumman
Katie Lewis Grumman@KatieLewisMIT·
⚡ Real-time video research: Expressive, conversational video agents built from a single image. Generalizes to any style and produces natural lip-sync at 24fps runwayml.com/news/building-…
English
0
0
0
247
Katie Lewis Grumman retweetledi
J Felipe Orozco
J Felipe Orozco@jforozcop·
The making of The Rogue. This project changed me creatively in a lot of ways. Spending years trying to figure out how to tell this story, and finally seeing it come alive the way I always dreamed it, still feels surreal. What I love about this BTS is that it shows how personal the process really was. All the experimenting, the little discoveries, the obsession with performances, camera movement, atmosphere, and emotion. This definitely feels like the beginning of a new chapter for filmmakers around the world searching for ways to finally bring their own stories to life. Extremely proud to be part of this moment and this revolution alongside the entire @runwayml team. Really happy to finally share this part too.
English
26
26
206
28.4K
Katie Lewis Grumman retweetledi
Runway
Runway@runwayml·
Today we're announcing Runway's expansion into Japan: we're opening a Tokyo office and investing an initial $40M in the country, as we build on what is already one of our largest and fastest-growing markets. We've tripled our enterprise customer base in the country in the last 12 months, with Japan becoming our third largest market globally. Companies like Yamaha, NHN and SoftBank are adopting Runway across marketing, advertising and creative content, and this expansion brings us closer to Japan's leading companies in gaming, media and robotics. Learn more about the initiative and the roles we're hiring for at the link below.
Runway tweet media
English
54
127
721
115K
Katie Lewis Grumman retweetledi
Marko Slavnic
Marko Slavnic@Markoslavnic·
The quality of animation you can create on your own is truly amazing. We really are just limited by our imaginations at this point. Go tell your story! Made in @runwayml in a few hours and a handful of gens.
English
856
1.2K
14.9K
6.7M
Katie Lewis Grumman retweetledi
Anastasis Germanidis
Anastasis Germanidis@agermanidis·
Runway added more than $40M in net new ARR so far this quarter, and we're less than halfway through. The biggest growth period in the history of the company. Generative video has hit its inflection point. Enterprises like Amazon and Robinhood are using Runway daily to reshape how they tell stories and reach customers, on our frontier video and world models. Thank you to our team and our customers. The best is yet to come.
English
32
29
284
87.6K

Keşfet

@yining_shi @runwayml @elonmusk @BarackObama @taylorswift13 @cristiano @BillGates @NASA