# Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision

arXiv: https://arxiv.org/abs/2601.19798 · HTML: https://mlsanity.com/paper/2601.19798/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- First posted on arXiv 27 Jan 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Built on by (most cited first, 15 of 15)

- [Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding](https://mlsanity.com/paper/2601.20430/) (2026)
- [Vision as Unified Multimodal Generation](https://mlsanity.com/paper/2607.06560/) (2026)
- [From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI](https://mlsanity.com/paper/2606.14502/) (2026)
- [Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding](https://mlsanity.com/paper/2605.07141/) (2026)
- [Unlocking Dense Metric Depth Estimation in VLMs](https://mlsanity.com/paper/2605.15876/) (2026)
- [Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models](https://mlsanity.com/paper/2606.08501/) (2026)
- [AgentCVR: Active Multi-Agent Cross-Video Reasoning via Script-Simulated Reinforcement Learning](https://mlsanity.com/paper/2605.29643/) (2026)
- [VIABLE: A Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation](https://mlsanity.com/paper/2605.31351/) (2026)
- [Mixture-of-Thought-Tokens: Unifying Perception and Reasoning for Free-form Multimodal Grounding](https://mlsanity.com/paper/2607.24407/) (2026)
- [BUS: Brain-Inspired Unsupervised Self-Reflection via Backward Prediction for Multimodal Reasoning](https://mlsanity.com/paper/2607.07361/) (2026)
- [Vision-Language Grounding as Bidirectional Concept Correspondence](https://mlsanity.com/paper/2608.07886/) (2026)
- [DepthEvidence: Unifying Metric Depth Prediction and Geometric Reasoning in Multimodal Language Models](https://mlsanity.com/paper/2609.31103/) (2026)
- [FORUM: Frozen Outputs Reconciled Using Model Agreement for Visual Grounding](https://mlsanity.com/paper/2609.37488/) (2026)
- [When Charts Deceive Web Agents: A Paired Benchmark for Misleading Visualization-Grounded Tasks](https://mlsanity.com/paper/2610.12823/) (2026)
- [ReferFlow: Beyond Final-Target Localization for Complex Referring Expressions](https://mlsanity.com/paper/2610.20352/) (2026)

## Abstract (arXiv)

Despite the significant advancements represented by Vision-Language Models (VLMs), current architectures often exhibit limitations in retaining fine-grained visual information, leading to coarse-grained multimodal comprehension. We attribute this deficiency to a suboptimal training paradigm inherent in prevailing VLMs, which exhibits a text-dominant optimization bias by conceptualizing visual signals merely as passive conditional inputs rather than supervisory targets. To mitigate this, we introduce Youtu-VL, a framework leveraging the Vision-Language Unified Autoregressive Supervision (VLUAS) paradigm, which fundamentally shifts the optimization objective from ``vision-as-input'' to ``vision-as-target.'' By integrating visual tokens directly into the prediction stream, Youtu-VL applies unified autoregressive supervision to both visual details and linguistic content. Furthermore, we extend this paradigm to encompass vision-centric tasks, enabling a standard VLM to perform vision-centric tasks without task-specific additions. Extensive empirical evaluations demonstrate that Youtu-VL achieves competitive performance on both general multimodal tasks and vision-centric tasks, establishing a robust foundation for the development of comprehensive generalist visual agents.