{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/geollava-8k-scaling-remote-sensing-multimodal","title":"GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution","arxiv_id":"2505.21375","date":"2025-05-27","proceeding":null,"authors":["Fengxiang Wang","Mingshuo Chen","Yueying Li","Di Wang","Haotian Wang","Zonghao Guo","Zefan Wang","Boqi Shan","Long Lan","Yulin Wang","Hongzhen Wang","Wenjing Yang","Bo Du","Jing Zhang"],"abstract":"Ultra-high-resolution (UHR) remote sensing (RS) imagery offers valuable data for Earth observation but pose challenges for existing multimodal foundation models due to two key bottlenecks: (1) limited availability of UHR training data, and (2) token explosion caused by the large image size. To address data scarcity, we introduce SuperRS-VQA (avg. 8,376$\\times$8,376) and HighRS-VQA (avg. 2,000$\\times$1,912), the highest-resolution vision-language datasets in RS to date, covering 22 real-world dialogue tasks. To mitigate token explosion, our pilot studies reveal significant redundancy in RS images: crucial information is concentrated in a small subset of object-centric tokens, while pruning background tokens (e.g., ocean or forest) can even improve performance. Motivated by these findings, we propose two strategies: Background Token Pruning and Anchored Token Selection, to reduce the memory footprint while preserving key semantics.Integrating these techniques, we introduce GeoLLaVA-8K, the first RS-focused multimodal large language model capable of handling inputs up to 8K$\\times$8K resolution, built on the LLaVA framework. Trained on SuperRS-VQA and HighRS-VQA, GeoLLaVA-8K sets a new state-of-the-art on the XLRS-Bench.","url_abs":"https://arxiv.org/abs/2505.21375v1","url_pdf":"https://arxiv.org/pdf/2505.21375v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"geollava-8k-scaling-remote-sensing-multimodal","repo_url":"https://github.com/MiliLab/GeoLLaVA-8K","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"8k"},{"task_slug":null,"task_name":"Avg"},{"task_slug":"earth-observation","task_name":"Earth Observation"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"multimodal-large-language-model","task_name":"Multimodal Large Language Model"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[{"slug":"superrs-vqa-highrs-vqa","name":"SuperRS-VQA, HighRS-VQA","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.21375","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}