World Wire

MirroS released Code-as-World : a paradigm that represents physical worlds through executable world representations. The argument is narrow and testable: pixels are evidence of a physical scene, not its ontology. A video model can predict plausible frames without ever representing mass, contact, or gravity. So instead of pixels, latents, or captions, Code-as-World represents a scene as executable code — a scene.json that MuJoCo can run, that an agent can verify against the source video, and that anyone can edit and re-simulate. An agentic loop recovers those programs from real footage in up to five rounds. The verified worlds then become training data with exact physical labels, which real video does not carry. Trained on that supervision, Code-as-World-VL-9B scores 55.4 MRA on QuantiPhy -validation, above Gemini-3.1 Flash at 54.8 and roughly 15 points above the strongest open-weight baseline. Is it deployable? Yes , at the research and internal-prototype tier. MirroS shi...

In this tutorial , we build an ensemble weather forecasting workflow with NVIDIA Earth2Studio . We install the required Earth2Studio components while preserving Colab’s existing CUDA-enabled PyTorch environment, load the FCN prognostic model, and retrieve atmospheric initial conditions from GFS. We then implement a custom wind-power diagnostic that converts 10-meter wind components into turbine capacity factors, along with a variable-scaled perturbation system that applies physically appropriate noise amplitudes to different atmospheric variables while retaining an unperturbed control member. Using Earth2Studio’s low-level iterator, coordinate-mapping, batching, and Zarr APIs, we construct our own ensemble execution pipeline, write forecast and diagnostic fields to a coordinate-aware data store, and verify the forecasts against GFS analyses using latitude-weighted RMSE, fair CRPS, ensemble spread, and spread-skill ratios. Finally, we visualize ensemble uncertainty through spatial maps...

Google has released Gemini Omni 1.1 Flash ( gemini-omni-1.1-flash ), a production update to its native multimodal video generation and editing model. The release moves Omni from a capable generator to a directable one: scene extension now reads up to 10 seconds of prior context instead of a single final frame, first and last frames can be pinned to control camera movement, drafts render in 360p at a third of 720p cost, finals upscale to 4K, and video clips can be passed as references for character consistency. Gemini Omni Flash is built on three properties Google distinguishes from prior video models: native multimodality (text, image, audio, and video processed together), conversational editing through the Interactions API , and world knowledge inherited from Gemini. Editing is stateful — you pass previous_interaction_id and the model applies your change while preserving what you did not mention, without re-uploading the prior video. Is it deployable? It is available th...