Runway 分享构建 Runway Agent 的技术方法

Joint video-and-action prediction suggests Runway is steering its research toward world models that could serve robotics and simulation, not just media generation. Developers and researchers working on embodied AI or interactive video should read the technical report for architectural details unavailable in most commercial releases. It offers a direct comparison point against open world-model efforts that typically disclose far less about training design.

Official accountRunway ML@runwaymlSource

Running on one RTX 5090 means hobbyists and university labs can now deploy a foundation robotics model without data-centre budgets, a sharp contrast to closed offerings from physical-AI startups. Teams using Hugging Face's LeRobot stack can clone the checkpoint and follow the published setup instructions to get a SO-101 arm running the same day. Watch this space as community-dataset-trained models challenge proprietary robotics stacks.

Official accountRunway ML@runwaymlSource

An open-weight, Apache 2.0 robot policy model that runs on a single RTX 5090 lowers the entry bar for robotics labs and hardware startups that cannot afford proprietary stacks. Teams building manipulation systems can fine-tune it locally instead of licensing closed models like GPT-6 Astra, which Runway claims is 51 times costlier per task. Builders tracking video-to-action transfer, an emerging alternative to pure imitation learning, should benchmark it on their own hardware.