paper-with-me

Papers

PEACE: Empowering Geologic Map Holistic Understanding with MLLMs

2025-01-10 · CVPR 2025 1 · Yangyu Huang, Tianyi Gao, Haoran Xu, QiHao Zhao, Yang song, Zhipeng Gui, Tengchao Lv, Hao Chen, Lei Cui, Scarlett Li, Furu Wei

Geologic map, as a fundamental diagram in geology science, provides critical insights into the structure and composition of Earth's subsurface and surface. These maps are indispensable in various fields, including disaster detection, resource exploration, and civil engineering. Despite their significance, current Multimodal Large Language Models (MLLMs) often fall short in geologic map understanding. This gap is primarily due to the challenging nature of cartographic generalization, which involves handling high-resolution map, managing multiple associated components, and requiring domain-specific knowledge. To quantify this gap, we construct GeoMap-Bench, the first-ever benchmark for evaluating MLLMs in geologic map understanding, which assesses the full-scale abilities in extracting, referring, grounding, reasoning, and analyzing. To bridge this gap, we introduce GeoMap-Agent, the inaugural agent designed for geologic map understanding, which features three modules: Hierarchical Information Extraction (HIE), Domain Knowledge Injection (DKI), and Prompt-enhanced Question Answering (PEQA). Inspired by the interdisciplinary collaboration among human scientists, an AI expert group acts as consultants, utilizing a diverse tool pool to comprehensively analyze questions. Through comprehensive experiments, GeoMap-Agent achieves an overall score of 0.811 on GeoMap-Bench, significantly outperforming 0.369 of GPT-4o. Our work, emPowering gEologic mAp holistiC undErstanding (PEACE) with MLLMs, paves the way for advanced AI applications in geology, enhancing the efficiency and accuracy of geological investigations.

📄 PDF Abstract BibTeX arXiv:2501.06184

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Fleming-VL: Towards Universal Medical Visual Reasoning with Multimodal LLMs

2025-11-02 · Yan Shu, Chi Liu, Robin Chen, Derek Li 외 arxiv

Multimodal Large Language Models (MLLMs) have demonstrated remarkable effectiveness in various general-domain scenarios, such as visual question answering and image captioning. Recently, researchers have increasingly foc…

Visual Question AnsweringImage CaptioningVisual Reasoning

Empowering Segmentation Ability to Multi-modal Large Language Models

2024-03-21 · YuQi Yang, Peng-Tao Jiang, Jing Wang, Hao Zhang 외

Multi-modal large language models (MLLMs) can understand image-language prompts and demonstrate impressive reasoning ability. In this paper, we extend MLLMs' output by empowering MLLMs with the segmentation ability. The …

Dialogue GenerationReasoning SegmentationSegmentationWord Embeddings

StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding

2024-11-06 · Junming Lin, Zheng Fang, Chi Chen, Zihao Wan 외

The rapid development of Multimodal Large Language Models (MLLMs) has expanded their capabilities from image comprehension to video understanding. However, most of these MLLMs focus primarily on offline video comprehensi…

Image ComprehensionStreaming video understandingVideo Understanding

InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling

2025-01-21 · Yi Wang, Xinhao Li, Ziang Yan, Yinan He 외

This paper aims to improve the performance of video multimodal large language models (MLLM) via long and rich context (LRC) modeling. As a result, we develop a new version of InternVideo2.5 with a focus on enhancing the …

Object TrackingReferring Expression SegmentationReferring Video Object SegmentationVideo Understanding

MineAgent: Towards Remote-Sensing Mineral Exploration with Multimodal Large Language Models

2024-12-23 · Beibei Yu, Tao Shen, Hongbin Na, Ling Chen 외

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-s…

Decision Making