🔮 RxBrain — Embodied Cognition Foundation Model

tencent/Hy-Embodied-RxBrain-1.0 — a unified Mixture-of-Transformers model that couples language reasoning with visual imagination. It answers questions about scenes, imagines images from text, and decomposes embodied tasks into interleaved step-by-step plans + goal images.

Tencent Robotics X × Futian Laboratory × Tencent Hunyuan · imagination decoded through a frozen FLUX VAE.

16 512
Examples
Image Question