---
source: 'https://howaiworks.ai/blog/youtu-vl-announcement'
section: blog
title: 'Youtu-VL: Unified Vision-Language Supervision'
description: >-
  Tencent Youtu Lab introduces Youtu-VL, a 4B parameter model that pioneers the
  'vision-as-target' paradigm for advanced visual perception.
date: '2026-01-30'
lastUpdated: '2026-07-21'
author: HowAIWorks Team
tags:
  - Computer Vision
  - Multimodal
  - Tencent
  - VLM
  - Open Source
  - Deep Learning
  - GGUF
  - ModelScope
readingTime: 6 minutes
---

# Youtu-VL: Unified Vision-Language Supervision

> Tencent Youtu Lab introduces Youtu-VL, a 4B parameter model that pioneers the 'vision-as-target' paradigm for advanced visual perception.

## Introduction

In the rapidly evolving landscape of Multimodal Large Language Models (MLLMs), many models excel at describing images but struggle with fine-grained visual tasks like precise object detection or depth estimation. This limitation often stems from a "text-dominant optimization bias," where visual signals are treated only as passive inputs.

Tencent Youtu Lab has addressed this challenge with the announcement of **Youtu-VL**, a versatile 4B-parameter model that introduces a fundamental shift in how vision and language are supervised. By pioneering the **Vision-Language Unified Autoregressive Supervision (VLUAS)** paradigm, Youtu-VL treats visual details not just as context, but as targets to be predicted, enabling a single model to master both conversational AI and dense visual perception.

## Key Innovation: Vision as Target

The core breakthrough of Youtu-VL is the shift from "vision-as-input" to **"vision-as-target"**. Traditional VLMs often drop redundant visual details during training because they are only optimized to generate text.

Youtu-VL solves this by:

- **Unified Multimodal Vocabulary**: Expanding the text lexicon to include a synergistic visual codebook of 150,000 tokens.
- **Autoregressive Vision Reconstruction**: During training, the model is tasked with reconstructing discrete visual tokens. This explicitly preserves dense visual information that is usually lost in standard VLM architectures.
- **Synergistic Vision Tokenizer**: A novel tokenizer that fuses semantic features from SigLIP-2 with geometric features from DINOv3, ensuring the model understands both "what" is in the image and "where" it is located.

## Architecture and Performance

Despite its compact size of **4 billion parameters**, Youtu-VL achieves [State-of-the-Art (SOTA)](https://howaiworks.ai/glossary/state-of-the-art-model) or highly competitive results across a wide array of benchmarks. It functions as a "generalist visual agent" that can perform complex vision-centric tasks without any specialized task-specific modules or heads.

### Vision-Centric Benchmarks

- **Visual Grounding**: Achieved 91.8% mAP on RefCOCO.
- **Object Detection**: 47.1% mAP on COCO 2017.
- **Semantic Segmentation**: 54.2 mIoU on ADE20k.
- **Depth Estimation**: High precision on NYUv2 (90.4% δ1).
- **Human Pose Estimation**: 89.1% PCKh@0.5 on MPII.

### Multimodal Reasoning

Beyond dense vision, Youtu-VL remains a powerful conversational partner. It scores significantly high on general multimodal benchmarks like MMBench (83.9) and DocVQA (94.4), showcasing its strength in OCR and complex reasoning.

## Open Source and Accessibility

Tencent has made Youtu-VL highly accessible to the developer community by releasing it on platforms like ModelScope and Hugging Face. Notably, the team has provided **GGUF quantized versions**, allowing researchers and enthusiasts to run this powerful 4B model on local machines using `llama.cpp`.

### Quickstart with llama.cpp

To run the Q8_0 quantized version locally, you can use the following command:

```bash
llama-server -hf tencent/Youtu-VL-4B-Instruct-GGUF:Q8_0 \
  --port 8080 \
  --image-max-tokens 2048 \
  --temp 0.1 \
  -n 12280
```

## Conclusion

Youtu-VL represents a significant step towards truly unified artificial intelligence. By breaking the silos between language modeling and computer vision tasks like segmentation and detection, Tencent Youtu Lab has provided a robust foundation for the next generation of visual agents. Its efficiency and performance make it a compelling choice for both edge deployment and large-scale multimodal research.

## Sources

- [Youtu-VL Technical Report (arXiv:2601.19798)](https://arxiv.org/abs/2601.19798)
- [ModelScope: Youtu-VL-4B-Instruct](https://modelscope.cn/models/Tencent-YouTu-Research/Youtu-VL-4B-Instruct)
- [ModelScope: Youtu-VL-4B-Instruct-GGUF](https://modelscope.cn/models/Tencent-YouTu-Research/Youtu-VL-4B-Instruct-GGUF)
- [Official GitHub Repository](https://github.com/TencentCloudADP/youtu-vl)

## Frequently Asked Questions

### What is Youtu-VL?

Youtu-VL is a lightweight yet robust 4B parameter Vision-Language Model developed by Tencent Youtu Lab, designed to bridge the gap between language understanding and fine-grained visual perception.

### What is the VLUAS paradigm?

VLUAS stands for Vision-Language Unified Autoregressive Supervision. It shifts the training objective from treatng vision as a passive input to a supervised target, explicitly reconstructing visual tokens alongside text.

### What vision-centric tasks can Youtu-VL perform?

Without task-specific modules, it can handle object detection, semantic segmentation, depth estimation, visual grounding, and human pose estimation.

### Is Youtu-VL available for local execution?

Yes, Tencent has released GGUF quantized versions (Q8_0, F16) which can be easily run using llama.cpp on consumer hardware.

---

Source: https://howaiworks.ai/blog/youtu-vl-announcement — HowAIWorks.ai