4 papers
FarSLIP: Discovering Effective CLIP Adaptation for Fine-Grained Remote Sensing Understanding
Zhenshi Li, Weikang Yu, Dilxat Muhtar +4
As CLIP's global alignment limits its ability to capture fine-grained details, recent efforts have focused on enhancing its region-text alignment. However, current remote sensing (…
Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models
Dilxat Muhtar, Enzhuo Zhang, Zhenshi Li +4
Vision-Language Models (VLMs) have demonstrated great potential in interpreting remote sensing (RS) images through language-guided semantic. However, the effectiveness of these VLM…
LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language Interpretation
Zhenshi Li, Dilxat Muhtar, Feng Gu +4
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…
StreamAdapter: Efficient Test Time Adaptation from Contextual Streams
Dilxat Muhtar, Yelong Shen, Yaming Yang +11
In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks directly from the given demonstrations without requiring gradient updates. While recent advances…