2 papers
cs.CV2026
GeoReason: Aligning Thinking And Answering In Remote Sensing Vision-Language Models Via Logical Consistency Reinforcement Learning
Wenshuai Li, Xiantai Xiang, Zixiao Wen +6
The evolution of Remote Sensing Vision-Language Models(RS-VLMs) emphasizes the importance of transitioning from perception-centric recognition toward high-level deductive reasoning…
cs.CV2026
SLGNet: Synergizing Structural Priors and Language-Guided Modulation for Multimodal Object Detection
Xiantai Xiang, Guangyao Zhou, Zixiao Wen +8
Multimodal object detection leveraging RGB and Infrared (IR) images is pivotal for robust perception in all-weather scenarios. While recent adapter-based approaches efficiently tra…