Tencent Releases Embodied Multimodal Model Hy-Embodied-VLM-1.0

_akhaliq · x · 2026-07-15

Tencent has released Hy-Embodied-VLM-1.0 on Hugging Face, an efficient MoE vision-language model designed for embodied agents.

Key details include:

This release leans heavily toward multimodal applications while showcasing significant research attributes.

Related event: Tencent Hunyuan Open-Sources Two Embodied AI Foundation Models(3 posts)→

Original post →

More from Multimodal

Multimodal channel →