Summary
According to a post on X by @QwenAIFans, Runway has released Praxis-1, a 27B-parameter world action model that predicts video and robot actions together. The release includes open weights and inference and fine-tuning code under Apache 2.0. Runway says the model solved 46.2% of 1,200 episodes on NVIDIA's RoboLab-120 benchmark and is best among world action models and open-source robot foundation models. The snippet is cut off, so the full comparison is not visible here.
AI-assisted summary based on the listed source.
What happened
Runway released Praxis-1, a 27B-parameter world action model that predicts video and robot actions together, with open weights and inference and fine-tuning code under Apache 2.0. Runway says it solved 46.2% of 1,200 episodes on NVIDIA's RoboLab-120 benchmark, best among world action models and open-source robot...
Why it matters
Robotics developers and researchers would be able to inspect, run and fine-tune the model if the open release is as described. The benchmark result comes from Runway's own claim, so independent testing on RoboLab-120 is the next thing to watch. The approach of predicting video and robot actions together is the detail to track for how robot foundation models are built.
Signal Intelligence
Signal Strength 95%
Technical label WATCH
Public Interest 39
Category OPEN SOURCE
Reader Depth TECHNICAL
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
Public Interest components
Recognizable Entity Score 0
Practical Impact Score 18
Novelty Interest Score 94
Consequence Score 46
Curiosity Score 48
Shareability Score 48
Why this is here
VQV surfaced this signal because it is recent, relevant to Robotics, connected to Scobleizer News Pulse (X).