InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911503542648832 |
|---|---|
| author | Tian, Changyao Yang, Danni Chen, Guanzhou Cui, Erfei Wang, Zhaokai Duan, Yuchen Yin, Penghao Chen, Sitao Yang, Ganlin Liu, Mingxin Zhu, Zirun Fan, Ziqian Gu, Leyao Wang, Haomin Wei, Qi Yin, Jinhui Yang, Xue Zhong, Zhihang Qin, Qi Xin, Yi Fu, Bin Liu, Yihao Ge, Jiaye Guo, Qipeng Luo, Gen Li, Hongsheng Qiao, Yu Chen, Kai Zhang, Hongjie |
| author_facet | Tian, Changyao Yang, Danni Chen, Guanzhou Cui, Erfei Wang, Zhaokai Duan, Yuchen Yin, Penghao Chen, Sitao Yang, Ganlin Liu, Mingxin Zhu, Zirun Fan, Ziqian Gu, Leyao Wang, Haomin Wei, Qi Yin, Jinhui Yang, Xue Zhong, Zhihang Qin, Qi Xin, Yi Fu, Bin Liu, Yihao Ge, Jiaye Guo, Qipeng Luo, Gen Li, Hongsheng Qiao, Yu Chen, Kai Zhang, Hongjie |
| contents | Unified multimodal models (UMMs) that integrate understanding, reasoning, generation, and editing face inherent trade-offs between maintaining strong semantic comprehension and acquiring powerful generation capabilities. In this report, we present InternVL-U, a lightweight 4B-parameter UMM that democratizes these capabilities within a unified framework. Guided by the principles of unified contextual modeling and modality-specific modular design with decoupled visual representations, InternVL-U integrates a state-of-the-art Multimodal Large Language Model (MLLM) with a specialized MMDiT-based visual generation head. To further bridge the gap between aesthetic generation and high-level intelligence, we construct a comprehensive data synthesis pipeline targeting high-semantic-density tasks, such as text rendering and scientific reasoning, under a reasoning-centric paradigm that leverages Chain-of-Thought (CoT) to better align abstract user intent with fine-grained visual generation details. Extensive experiments demonstrate that InternVL-U achieves a superior performance - efficiency balance. Despite using only 4B parameters, it consistently outperforms unified baseline models with over 3x larger scales such as BAGEL (14B) on various generation and editing tasks, while retaining strong multimodal understanding and reasoning capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09877 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing Tian, Changyao Yang, Danni Chen, Guanzhou Cui, Erfei Wang, Zhaokai Duan, Yuchen Yin, Penghao Chen, Sitao Yang, Ganlin Liu, Mingxin Zhu, Zirun Fan, Ziqian Gu, Leyao Wang, Haomin Wei, Qi Yin, Jinhui Yang, Xue Zhong, Zhihang Qin, Qi Xin, Yi Fu, Bin Liu, Yihao Ge, Jiaye Guo, Qipeng Luo, Gen Li, Hongsheng Qiao, Yu Chen, Kai Zhang, Hongjie Computer Vision and Pattern Recognition Unified multimodal models (UMMs) that integrate understanding, reasoning, generation, and editing face inherent trade-offs between maintaining strong semantic comprehension and acquiring powerful generation capabilities. In this report, we present InternVL-U, a lightweight 4B-parameter UMM that democratizes these capabilities within a unified framework. Guided by the principles of unified contextual modeling and modality-specific modular design with decoupled visual representations, InternVL-U integrates a state-of-the-art Multimodal Large Language Model (MLLM) with a specialized MMDiT-based visual generation head. To further bridge the gap between aesthetic generation and high-level intelligence, we construct a comprehensive data synthesis pipeline targeting high-semantic-density tasks, such as text rendering and scientific reasoning, under a reasoning-centric paradigm that leverages Chain-of-Thought (CoT) to better align abstract user intent with fine-grained visual generation details. Extensive experiments demonstrate that InternVL-U achieves a superior performance - efficiency balance. Despite using only 4B parameters, it consistently outperforms unified baseline models with over 3x larger scales such as BAGEL (14B) on various generation and editing tasks, while retaining strong multimodal understanding and reasoning capabilities. |
| title | InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.09877 |