Symbolic Representation for Any-to-Any Generative Tasks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917997368573952 |
|---|---|
| author | Chen, Jiaqi Zhu, Xiaoye Wang, Yue Liu, Tianyang Chen, Xinhui Chen, Ying Leong, Chak Tou Ke, Yifei Liu, Joseph Yuan, Yiwen McAuley, Julian Li, Li-jia |
| author_facet | Chen, Jiaqi Zhu, Xiaoye Wang, Yue Liu, Tianyang Chen, Xinhui Chen, Ying Leong, Chak Tou Ke, Yifei Liu, Joseph Yuan, Yiwen McAuley, Julian Li, Li-jia |
| contents | We propose a symbolic generative task description language and a corresponding inference engine capable of representing arbitrary multimodal tasks as structured symbolic flows. Unlike conventional generative models that rely on large-scale training and implicit neural representations to learn cross-modal mappings, often at high computational cost and with limited flexibility, our framework introduces an explicit symbolic representation comprising three core primitives: functions, parameters, and topological logic. Leveraging a pre-trained language model, our inference engine maps natural language instructions directly to symbolic workflows in a training-free manner. Our framework successfully performs over 12 diverse multimodal generative tasks, demonstrating strong performance and flexibility without the need for task-specific tuning. Experiments show that our method not only matches or outperforms existing state-of-the-art unified models in content quality, but also offers greater efficiency, editability, and interruptibility. We believe that symbolic task representations provide a cost-effective and extensible foundation for advancing the capabilities of generative AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17261 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Symbolic Representation for Any-to-Any Generative Tasks Chen, Jiaqi Zhu, Xiaoye Wang, Yue Liu, Tianyang Chen, Xinhui Chen, Ying Leong, Chak Tou Ke, Yifei Liu, Joseph Yuan, Yiwen McAuley, Julian Li, Li-jia Machine Learning Artificial Intelligence We propose a symbolic generative task description language and a corresponding inference engine capable of representing arbitrary multimodal tasks as structured symbolic flows. Unlike conventional generative models that rely on large-scale training and implicit neural representations to learn cross-modal mappings, often at high computational cost and with limited flexibility, our framework introduces an explicit symbolic representation comprising three core primitives: functions, parameters, and topological logic. Leveraging a pre-trained language model, our inference engine maps natural language instructions directly to symbolic workflows in a training-free manner. Our framework successfully performs over 12 diverse multimodal generative tasks, demonstrating strong performance and flexibility without the need for task-specific tuning. Experiments show that our method not only matches or outperforms existing state-of-the-art unified models in content quality, but also offers greater efficiency, editability, and interruptibility. We believe that symbolic task representations provide a cost-effective and extensible foundation for advancing the capabilities of generative AI. |
| title | Symbolic Representation for Any-to-Any Generative Tasks |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2504.17261 |