Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2412.17339 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915076092461056 |
|---|---|
| author | Yu, Beibei Shen, Tao Na, Hongbin Chen, Ling Li, Denqi |
| author_facet | Yu, Beibei Shen, Tao Na, Hongbin Chen, Ling Li, Denqi |
| contents | Remote-sensing mineral exploration is critical for identifying economically viable mineral deposits, yet it poses significant challenges for multimodal large language models (MLLMs). These include limitations in domain-specific geological knowledge and difficulties in reasoning across multiple remote-sensing images, further exacerbating long-context issues. To address these, we present MineAgent, a modular framework leveraging hierarchical judging and decision-making modules to improve multi-image reasoning and spatial-spectral integration. Complementing this, we propose MineBench, a benchmark specific for evaluating MLLMs in domain-specific mineral exploration tasks using geological and hyperspectral data. Extensive experiments demonstrate the effectiveness of MineAgent, highlighting its potential to advance MLLMs in remote-sensing mineral exploration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_17339 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MineAgent: Towards Remote-Sensing Mineral Exploration with Multimodal Large Language Models Yu, Beibei Shen, Tao Na, Hongbin Chen, Ling Li, Denqi Artificial Intelligence Computation and Language Remote-sensing mineral exploration is critical for identifying economically viable mineral deposits, yet it poses significant challenges for multimodal large language models (MLLMs). These include limitations in domain-specific geological knowledge and difficulties in reasoning across multiple remote-sensing images, further exacerbating long-context issues. To address these, we present MineAgent, a modular framework leveraging hierarchical judging and decision-making modules to improve multi-image reasoning and spatial-spectral integration. Complementing this, we propose MineBench, a benchmark specific for evaluating MLLMs in domain-specific mineral exploration tasks using geological and hyperspectral data. Extensive experiments demonstrate the effectiveness of MineAgent, highlighting its potential to advance MLLMs in remote-sensing mineral exploration. |
| title | MineAgent: Towards Remote-Sensing Mineral Exploration with Multimodal Large Language Models |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2412.17339 |