Our Research
Building general-purpose multimodal
simulators of the world.
We believe models that use video as their main input/output modality, when supplemented by other modalities like text and audio, will form the next paradigm of computing.
We're advancing research in AI systems that can understand and simulate the world and its dynamics.
RNA Sessions
An ongoing series of talks about frontier research in
AI and art, hosted by Runway.Learn moreIntroducing General World Models
Research /
December 11, 2023
More control, fidelity and expressibility
Research /
November 23, 2023
Mitigating stereotypical biases in text to image generative systems
Research /
October 10, 2023
Scale, Speed and Stepping Stones: The path to Gen-2
Research /
September 28, 2023
Gen-2: Generate novel videos with text, images or video clips
Research /
March 11, 2023
Gen-1: The next step forward for generative AI
Research /
December 11, 2022
Towards unified keyframe propagation models
Research /
May 25, 2022
High-Resolution Image Synthesis with Latent Diffusion Models
Research /
April 13, 2022
Soundify: Matching sound effects to video
Research /
January 11, 2022
Distributing Work: Adventures in queuing
Research /
November 1, 2021
Creative AI Conversations 2021 - 2022
Research /
September 1, 2021