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:
- Activates only 3B parameters per token
- Achieves SOTA on 19 out of 38 benchmarks
- Primarily targets embodied agents scenarios
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)→
More from Multimodal
- FLUX.2 Klein Drifts Hard on Character Expressions While Free Gemini Holds Likeness — wacomlover · 2026-09-11
- Tencent Hunyuan releases AuK code and weights on GitHub with ComfyUI and fine-tuning support — aigclink · 2026-09-11
- Creator turns Bahamut vs Tiamat rivalry into an AI cinematic battle with Midjourney, GPT Image 2 and Seedance — azed_ai · 2026-09-11
- invideo launches AI agent-powered editor to automate repetitive editing tasks — azed_ai · 2026-09-11
- fable 5.1 recreates The Starry Night with 256,157 JavaScript brush strokes — cedric_chee · 2026-09-11
- GPT-6 Astra + Hyper3D Rodin MCP Generates 3D Assets in One Agent Flow — ahuja_priyank · 2026-09-11