From one public sample to multi-episode embodied-AI experiments.
Read down the page in order. The roadmap keeps stage timing, research tracks, linked tasks, scale-up gates, and source mirrors visible without asking readers to click through a separate track selector.
What has shipped, what is active, and what remains future work.
The timeline keeps implementation state separate from ambition: public-sample task work, selected-episode baselines, Qwen3-Omni diagnostics, branch experiments, and the long-range pretraining goal.
Four tracks with their task evidence kept together.
Each track lists the linked 20-task-suite heads, current evidence state, next steps, and extension probes in one card. Nothing is hidden behind a selected-track side panel.
Data preparation and model-branch decisions.
This section keeps the selected-episode gate, Qwen3-Omni pilot contract, and foundation-model branch matrix separate from the task cards so readers can see the training route clearly.
All task contracts in one index.
The compact task index is for scanning. It shows each task’s output, metric, and direction roles without forcing another navigation layer.
Structured mirrors for scripts and validators are attached here after the reader page. Most readers should use the sections above before opening these records.