# Tencent Releases 2B Vision Model for Robotics

> The new HY-Embodied 0.5 is a vision-language model designed specifically for multi-object tracking in dynamic, real-world environments.

Published by The Open Weights on Apr 2, 2026. Canonical: https://theopenweights.com/news/hy-embodied-0-5-bhzk

## Key facts

- Company: Tencent
- Model: HY-Embodied 0.5
- Version: 0.5
- Category: Vision-Language
- Modalities: Vision-Language
- License: Other (Open weights, commercial use allowed)
- Parameters: 2B
- Context window: 262K tokens
- Architecture: HunYuanVLMoTForConditionalGeneration
- Precision: BF16
- Significance: notable
- Published: 2026-04-02
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/tencent/HY-Embodied-0.5
- Canonical URL: https://theopenweights.com/news/hy-embodied-0-5-bhzk

Tencent's Hunyuan team has released HY-Embodied 0.5, a new 2-billion-parameter vision-language model aimed at the growing field of embodied AI.

Unlike many general-purpose VLMs that focus on static image captioning, HY-Embodied is built on an end-to-end Multi-object Tracking (MoT) architecture. This allows the model to perceive and follow multiple distinct objects through video sequences—a critical capability for robots and other autonomous agents that need to understand dynamic scenes.

## A Foundation for Physical Agents

The model's specialized design bridges the gap between passive visual understanding and the active interaction required in robotics. By providing a unified system for tracking objects over time, HY-Embodied could enable more sophisticated behaviors in applications like:

* Robotic navigation and manipulation
* Autonomous vehicle systems
* Advanced video analysis

The release signals a move towards creating foundational models for specific, complex domains beyond simple text and image generation. The [HY-Embodied 0.5 model](https://huggingface.co/tencent/HY-Embodied-0.5) is available on Hugging Face under a custom license agreement.

## Get the model

- [Hugging Face](https://huggingface.co/tencent/HY-Embodied-0.5)

## Sources

- [tencent/HY-Embodied-0.5](https://huggingface.co/tencent/HY-Embodied-0.5) — Hugging Face, Apr 2, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Tencent Releases 2B Vision Model for Robotics", The Open Weights, Apr 2, 2026, https://theopenweights.com/news/hy-embodied-0-5-bhzk