English

Singpath-VL Technical Report

Computer Vision and Pattern Recognition 2026-02-13 v2

Abstract

We present Singpath-VL, a vision-language large model, to fill the vacancy of AI assistant in cervical cytology. Recent advances in multi-modal large language models (MLLMs) have significantly propelled the field of computational pathology. However, their application in cytopathology, particularly cervical cytology, remains underexplored, primarily due to the scarcity of large-scale, high-quality annotated datasets. To bridge this gap, we first develop a novel three-stage pipeline to synthesize a million-scale image-description dataset. The pipeline leverages multiple general-purpose MLLMs as weak annotators, refines their outputs through consensus fusion and expert knowledge injection, and produces high-fidelity descriptions of cell morphology. Using this dataset, we then fine-tune the Qwen3-VL-4B model via a multi-stage strategy to create a specialized cytopathology MLLM. The resulting model, named Singpath-VL, demonstrates superior performance in fine-grained morphological perception and cell-level diagnostic classification. To advance the field, we will open-source a portion of the synthetic dataset and benchmark.

Keywords

Cite

@article{arxiv.2602.09523,
  title  = {Singpath-VL Technical Report},
  author = {Zhen Qiu and Kaiwen Xiao and Zhengwei Lu and Xiangyu Liu and Lei Zhao and Hao Zhang},
  journal= {arXiv preprint arXiv:2602.09523},
  year   = {2026}
}
R2 v1 2026-07-01T10:29:19.706Z