GeoUni: A Unified Model for Generating Geometry Diagrams, Problems and Problem Solutions
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913825999028224 |
|---|---|
| author | Cheng, Jo-Ku Zhang, Zeren Chen, Ran Deng, Jingyang Qin, Ziran Ma, Jinwen |
| author_facet | Cheng, Jo-Ku Zhang, Zeren Chen, Ran Deng, Jingyang Qin, Ziran Ma, Jinwen |
| contents | We propose GeoUni, the first unified geometry expert model capable of generating problem solutions and diagrams within a single framework in a way that enables the creation of unique and individualized geometry problems. Traditionally, solving geometry problems and generating diagrams have been treated as separate tasks in machine learning, with no models successfully integrating both to support problem creation. However, we believe that mastery in geometry requires frictionless integration of all of these skills, from solving problems to visualizing geometric relationships, and finally, crafting tailored problems. Our extensive experiments demonstrate that GeoUni, with only 1.5B parameters, achieves performance comparable to larger models such as DeepSeek-R1 with 671B parameters in geometric reasoning tasks. GeoUni also excels in generating precise geometric diagrams, surpassing both text-to-image models and unified models, including the GPT-4o image generation. Most importantly, GeoUni is the only model capable of successfully generating textual problems with matching diagrams based on specific knowledge points, thus offering a wider range of capabilities that extend beyond current models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10146 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GeoUni: A Unified Model for Generating Geometry Diagrams, Problems and Problem Solutions Cheng, Jo-Ku Zhang, Zeren Chen, Ran Deng, Jingyang Qin, Ziran Ma, Jinwen Machine Learning Artificial Intelligence We propose GeoUni, the first unified geometry expert model capable of generating problem solutions and diagrams within a single framework in a way that enables the creation of unique and individualized geometry problems. Traditionally, solving geometry problems and generating diagrams have been treated as separate tasks in machine learning, with no models successfully integrating both to support problem creation. However, we believe that mastery in geometry requires frictionless integration of all of these skills, from solving problems to visualizing geometric relationships, and finally, crafting tailored problems. Our extensive experiments demonstrate that GeoUni, with only 1.5B parameters, achieves performance comparable to larger models such as DeepSeek-R1 with 671B parameters in geometric reasoning tasks. GeoUni also excels in generating precise geometric diagrams, surpassing both text-to-image models and unified models, including the GPT-4o image generation. Most importantly, GeoUni is the only model capable of successfully generating textual problems with matching diagrams based on specific knowledge points, thus offering a wider range of capabilities that extend beyond current models. |
| title | GeoUni: A Unified Model for Generating Geometry Diagrams, Problems and Problem Solutions |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2504.10146 |