Machine LearningAI Research4 min reading time

Meet ‘Code-as-World’: An Agentic Loop That Rewrites Real Videos Into Executable MuJoCo Physics Programs

MarkTechPost
Read full post
MirroS introduced Code-as-World, a method that converts real videos into executable MuJoCo physics programs representing physical scenes as code. This approach enables precise physical modeling and outperforms previous models on physics benchmarks. The team released the model checkpoints and code under Apache 2.0 for research use.

More in Machine Learning

Machine Learning3 min read

Nvidia and Palantir fine-tune a 30B Nemotron model for Nvidia’s supply chain. It beats a model 18 times its size.

Covered by 3 sources
Machine Learning6 min read

CoreWeave Puts Field Engineers Inside Customer Teams for Physical AI

Covered by 2 sources
Machine Learning2 min read

Weatherwatch: AI model beats standard methods at predicting cyclones

The Guardian