Skip to main content
Search

# PhysBrain 1.5

1 related articles

Subscribe to updates
  1. PhysBrain 1.5: A Physical Foundation Model Unifying Language, Action, and Future World States in One Autoregressive Vocabulary

    PhysBrain 1.5 builds on a pretrained Qwen3-VL backbone extended with dedicated action and visual-state tokens, formulating language responses, structured spatial outputs, end-effector trajectories, and future world states as discrete tokens jointly learned under a single next-token prediction objective, with embodied pretraining supervision drawn entirely from human interaction videos (egocentric, synchronized ego-exocentric, and panoramic recordings structured into task-centered episodes) and supervised fine-tuning combining human demonstrations, real-robot trajectories, and simulated experience; across 28 embodied spatial-intelligence and planning benchmarks the 8B version reaches an overall average of 72.

You’re all caught up