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

zhixiangwei, Yi Li, Zane, Xinghua Jiang, Zuwei Long, ShifengLiu, Hongze Shen, Wei Liu, Xiaoyu Tan, Haojia Lin, Yubo Zhu, Qianyu Li, DI YIN, caohaoyu, Weibo Gu, Xin Li, Yinsong Liu, Deqiang Jiang, XING SUN, Yunsheng Wu, Mingkong Tang, Shuangyin Liu, Lexiang Tang, HaoDong Lin, Junrulu, JR QIN, Lingfeng Qiao, Ruizhi Qiao, Bo Ke, Jianfeng He, Ke Li, Yangning Li, 沈云航 Yunhang Shen, Mengdan Zhang, Peixian Chen, Kun Yin, Bing Liu, Yunfei Wu, Huang Chen, Zhongpeng Cai, Xiaotian Li

Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision: 30 upvotes on Hugging Face Daily Papers, #4 of 21 papers on 2026-01-28. Day-by-day upvote history. It lost 14 votes when the Hub removed votes in bulk.

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.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.