5 papers
Shattering the Shortcut: A Topology-Regularized Benchmark for Multi-hop Medical Reasoning in LLMs
Xing Zi, Xinying Zhou, Jinghao Xiao +2
While Large Language Models (LLMs) achieve expert-level performance on standard medical benchmarks through single-hop factual recall, they severely struggle with the complex, multi…
Beyond Pixels: A Training-Free, Text-to-Text Framework for Remote Sensing Image Retrieval
J. Xiao, Y. Guo, X. Zi +3
Semantic retrieval of remote sensing (RS) images is a critical task fundamentally challenged by the \textquote{semantic gap}, the discrepancy between a model's low-level visual fea…
RSVLM-QA: A Benchmark Dataset for Remote Sensing Vision Language Model-based Question Answering
Xing Zi, Jinghao Xiao, Yunxiao Shi +4
Visual Question Answering (VQA) in remote sensing (RS) is pivotal for interpreting Earth observation data. However, existing RS VQA datasets are constrained by limitations in annot…
AeroLite: Tag-Guided Lightweight Generation of Aerial Image Captions
Xing Zi, Tengjun Ni, Xianjing Fan +4
Accurate and automated captioning of aerial imagery is crucial for applications like environmental monitoring, urban planning, and disaster management. However, this task remains c…
Visual and Text Prompt Segmentation: A Novel Multi-Model Framework for Remote Sensing
Xing Zi, Kairui Jin, Xian Tao +4
Pixel-level segmentation is essential in remote sensing, where foundational vision models like CLIP and Segment Anything Model(SAM) have demonstrated significant capabilities in ze…