Unlocking Zero-Shot Geospatial Reasoning via Indirect Rewards
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914522494664704 |
|---|---|
| author | Xu, Chenhui Yu, Fuxun Bianco, Michael J. Kovarskiy, Jacob Tang, Raphael Zhang, Qi Xu, Zirui LeVine, Will Dubbs, Brandon Liao, Heming Burgess, Cassandra Bag, Suvam Patravali, Jay Kukal, Rupanjali Figueroa, Mikael Madhok, Rishi Karianakis, Nikolaos Xiong, Jinjun |
| author_facet | Xu, Chenhui Yu, Fuxun Bianco, Michael J. Kovarskiy, Jacob Tang, Raphael Zhang, Qi Xu, Zirui LeVine, Will Dubbs, Brandon Liao, Heming Burgess, Cassandra Bag, Suvam Patravali, Jay Kukal, Rupanjali Figueroa, Mikael Madhok, Rishi Karianakis, Nikolaos Xiong, Jinjun |
| contents | Training robust reasoning vision-language models (VLMs) in rare domains (such as geospatial) is fundamentally constrained by supervision scarcity. While raw geospatial imagery is abundant, the amount of task-direct supervision falls far behind that of common domains. In this work, we validate an important conclusion: indirect verifiable rewards, derived from seemingly unrelated metadata, are sufficient to induce sophisticated and generalizable geospatial reasoning across a wide range of downstream tasks (25+). We present Geo-R1 as one empirical instantiation of this paradigm. Rather than relying on limited task-specific annotations (i.e., direct rewards), Geo-R1 utilizes scalable, verifiable indirect proxy rewards based on cross-view alignment with metadata (geolocation information) to drive reinforcement learning at scale. Such indirect rewards successfully motivate the model to discover and internalize zero-shot geospatial reasoning across diverse tasks, achieving extraordinary zero-shot transfer on out-of-distribution benchmarks and even surpassing fully supervised specialists on certain benchmarks. These findings indicate that optimizing for indirect verifiable rewards may provide a scalable pathway to unlock generalized reasoning capabilities in rare domains with massive unlabeled data archives. Our code is availavle at: https://github.com/miniHuiHui/Geo-R1. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_00072 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unlocking Zero-Shot Geospatial Reasoning via Indirect Rewards Xu, Chenhui Yu, Fuxun Bianco, Michael J. Kovarskiy, Jacob Tang, Raphael Zhang, Qi Xu, Zirui LeVine, Will Dubbs, Brandon Liao, Heming Burgess, Cassandra Bag, Suvam Patravali, Jay Kukal, Rupanjali Figueroa, Mikael Madhok, Rishi Karianakis, Nikolaos Xiong, Jinjun Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Training robust reasoning vision-language models (VLMs) in rare domains (such as geospatial) is fundamentally constrained by supervision scarcity. While raw geospatial imagery is abundant, the amount of task-direct supervision falls far behind that of common domains. In this work, we validate an important conclusion: indirect verifiable rewards, derived from seemingly unrelated metadata, are sufficient to induce sophisticated and generalizable geospatial reasoning across a wide range of downstream tasks (25+). We present Geo-R1 as one empirical instantiation of this paradigm. Rather than relying on limited task-specific annotations (i.e., direct rewards), Geo-R1 utilizes scalable, verifiable indirect proxy rewards based on cross-view alignment with metadata (geolocation information) to drive reinforcement learning at scale. Such indirect rewards successfully motivate the model to discover and internalize zero-shot geospatial reasoning across diverse tasks, achieving extraordinary zero-shot transfer on out-of-distribution benchmarks and even surpassing fully supervised specialists on certain benchmarks. These findings indicate that optimizing for indirect verifiable rewards may provide a scalable pathway to unlock generalized reasoning capabilities in rare domains with massive unlabeled data archives. Our code is availavle at: https://github.com/miniHuiHui/Geo-R1. |
| title | Unlocking Zero-Shot Geospatial Reasoning via Indirect Rewards |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2510.00072 |