Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yu, Beibei, Shen, Tao, Na, Hongbin, Chen, Ling, Li, Denqi
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