Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.21172 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910895403171840 |
|---|---|
| author | Chen, Jingye Zhao, Yuzhong Huang, Yupan Cui, Lei Dong, Li Lv, Tengchao Chen, Qifeng Wei, Furu |
| author_facet | Chen, Jingye Zhao, Yuzhong Huang, Yupan Cui, Lei Dong, Li Lv, Tengchao Chen, Qifeng Wei, Furu |
| contents | Recent advances in generative models have significantly impacted game generation. However, despite producing high-quality graphics and adequately receiving player input, existing models often fail to maintain fundamental game properties such as numerical and spatial consistency. Numerical consistency ensures gameplay mechanics correctly reflect score changes and other quantitative elements, while spatial consistency prevents jarring scene transitions, providing seamless player experiences. In this paper, we revisit the paradigm of generative games to explore what truly constitutes a Model as a Game (MaaG) with a well-developed mechanism. We begin with an empirical study on ``Traveler'', a 2D game created by an LLM featuring minimalist rules yet challenging generative models in maintaining consistency. Based on the DiT architecture, we design two specialized modules: (1) a numerical module that integrates a LogicNet to determine event triggers, with calculations processed externally as conditions for image generation; and (2) a spatial module that maintains a map of explored areas, retrieving location-specific information during generation and linking new observations to ensure continuity. Experiments across three games demonstrate that our integrated modules significantly enhance performance on consistency metrics compared to baselines, while incurring minimal time overhead during inference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21172 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Model as a Game: On Numerical and Spatial Consistency for Generative Games Chen, Jingye Zhao, Yuzhong Huang, Yupan Cui, Lei Dong, Li Lv, Tengchao Chen, Qifeng Wei, Furu Computer Vision and Pattern Recognition Recent advances in generative models have significantly impacted game generation. However, despite producing high-quality graphics and adequately receiving player input, existing models often fail to maintain fundamental game properties such as numerical and spatial consistency. Numerical consistency ensures gameplay mechanics correctly reflect score changes and other quantitative elements, while spatial consistency prevents jarring scene transitions, providing seamless player experiences. In this paper, we revisit the paradigm of generative games to explore what truly constitutes a Model as a Game (MaaG) with a well-developed mechanism. We begin with an empirical study on ``Traveler'', a 2D game created by an LLM featuring minimalist rules yet challenging generative models in maintaining consistency. Based on the DiT architecture, we design two specialized modules: (1) a numerical module that integrates a LogicNet to determine event triggers, with calculations processed externally as conditions for image generation; and (2) a spatial module that maintains a map of explored areas, retrieving location-specific information during generation and linking new observations to ensure continuity. Experiments across three games demonstrate that our integrated modules significantly enhance performance on consistency metrics compared to baselines, while incurring minimal time overhead during inference. |
| title | Model as a Game: On Numerical and Spatial Consistency for Generative Games |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.21172 |