paper-with-me

Papers

LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language Interpretation

2024-11-14 · Zhenshi Li, Dilxat Muhtar, Feng Gu, Xueliang Zhang, Pengfeng Xiao, Guangjun He, Xiaoxiang Zhu

Automatically and rapidly understanding Earth's surface is fundamental to our grasp of the living environment and informed decision-making. This underscores the need for a unified system with comprehensive capabilities in analyzing Earth's surface to address a wide range of human needs. The emergence of multimodal large language models (MLLMs) has great potential in boosting the efficiency and convenience of intelligent Earth observation. These models can engage in human-like conversations, serve as unified platforms for understanding images, follow diverse instructions, and provide insightful feedbacks. In this study, we introduce LHRS-Bot-Nova, an MLLM specialized in understanding remote sensing (RS) images, designed to expertly perform a wide range of RS understanding tasks aligned with human instructions. LHRS-Bot-Nova features an enhanced vision encoder and a novel bridge layer, enabling efficient visual compression and better language-vision alignment. To further enhance RS-oriented vision-language alignment, we propose a large-scale RS image-caption dataset, generated through feature-guided image recaptioning. Additionally, we introduce an instruction dataset specifically designed to improve spatial recognition abilities. Extensive experiments demonstrate superior performance of LHRS-Bot-Nova across various RS image understanding tasks. We also evaluate different MLLM performances in complex RS perception and instruction following using a complicated multi-choice question evaluation benchmark, providing a reliable guide for future model selection and improvement. Data, code, and models will be available at https://github.com/NJU-LHRS/LHRS-Bot.

📄 PDF Abstract BibTeX arXiv:2411.09301

Code (1)

NJU-LHRS/LHRS-Bot 공식 구현 pytorch

Tasks

Earth ObservationInstruction FollowingLanguage ModelingLanguage ModellingLarge Language ModelModel SelectionMultimodal Large Language Model

Similar Papers 제목 키워드 기반

LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model

2024-02-04 · Dilxat Muhtar, Zhenshi Li, Feng Gu, Xueliang Zhang 외

The revolutionary capabilities of large language models (LLMs) have paved the way for multimodal large language models (MLLMs) and fostered diverse applications across various specialized domains. In the remote sensing (…

Language ModelingLanguage Modelling

PP-DocBee2: Improved Baselines with Efficient Data for Multimodal Document Understanding

2025-06-22 · Kui Huang, Xinrong Chen, Wenyu Lv, Jincheng Liao 외

This report introduces PP-DocBee2, an advanced version of the PP-DocBee, designed to enhance multimodal document understanding. Built on a large multimodal model architecture, PP-DocBee2 addresses the limitations of its …

document understanding

RemoteSAM: Towards Segment Anything for Earth Observation

2025-05-23 · Liang Yao, Fan Liu, Delong Chen, Chuanyi Zhang 외

We aim to develop a robust yet flexible visual foundation model for Earth observation. It should possess strong capabilities in recognizing and localizing diverse visual targets while providing compatibility with various…

AttributeEarth ObservationReferring ExpressionReferring Expression Segmentation

DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative Decoding

2025-05-25 · Yunhai Hu, Tianhua Xia, Zining Liu, Rahul Raman 외

Speculative decoding (SD) has emerged as a powerful method for accelerating autoregressive generation in large language models (LLMs), yet its integration into vision-language models (VLMs) remains underexplored. We intr…

feature selection

Innovator-VL: A Multimodal Large Language Model for Scientific Discovery

2026-01-27 · Zichen Wen, Boxue Yang, Shuang Chen, Yaojie Zhang 외 arxiv

We present Innovator-VL, a scientific multimodal large language model designed to advance understanding and reasoning across diverse scientific domains while maintaining excellent performance on general vision tasks. Con…

Reinforcement LearningMultimodal Reasoning