HY-Embodied-0.5

HY-Embodied-0.5 is the embodied Vision-Language Model (VLM) foundation model from the HY-Embodied project. It comes in two variants: a 2B activated-parameter model for edge deployment and a 32B activated-parameter model for complex reasoning. It adopts a Mixture-of-Transformers (MoT) architecture with modality-specific computing and latent tokens for enhanced perceptual representation. The model achieves state-of-the-art performance across 22 benchmarks spanning visual perception, spatial reasoning, and embodied understanding.