Fangxin Shang portrait

Fangxin Shang

Senior Algorithm Expert, Qifu Technology

My ideal is to build multimodal AGI: AI systems that can perceive, understand, and reason over visual, audio, textual, and structured signals in complex real-world environments.

I currently work on multimodal intelligence for credit and financial scenarios, including multimodal benchmarks and real-time audio-video analysis for financial due diligence. Previously, I worked on medical multimodal intelligence at Baidu, covering medical image analysis, biomedical vision-language models, synthetic medical data, and medical AI platforms.

[ Google Scholar ] [ GitHub ] [ Email ]

332Citations
10h-index
10i10-index

Google Scholar snapshot, September 15, 2026.

Short BIO

Fangxin Shang is a senior algorithm expert at Qifu Technology. His current work focuses on multimodal intelligence for credit and financial scenarios, especially systems that integrate visual, audio, textual, and structured evidence for reliable domain understanding and decision support.

Before joining Qifu Technology, he worked at Baidu from 2019 to 2025, where he led and contributed to multiple medical AI systems, including healthcare multimodal large models, medical image analysis platforms, lung CT analysis, fundus disease screening, and large-scale medical simulation systems. His long-term research interest is to build useful and trustworthy multimodal AGI for complex real-world environments.

Research Interests

Publication

Synced with Google Scholar after the latest profile update. Citation counts are not shown for every paper to keep the page easy to maintain.

2026

  1. Fangxin Shang, Yehui Yang. Hypothesis-Driven Skill Optimization for LLM Agents. arXiv preprint arXiv:2606.22330, 2026. [ arXiv ]
  2. Rui Cui, Fangxin Shang, Yehui Yang, Qing Yang, Yanwu Xu, Tao Chen. FCMBench-Video: Benchmarking Document Video Intelligence. arXiv preprint arXiv:2604.25186, 2026. [ arXiv ] [ GitHub ] [ HuggingFace ]
  3. Lingdong Shen, Xiaoshuang Huang, Fangxin Shang, Xiaosong Zhang, Yehui Yang, Bin Fan, Shiming Xiang. From Image to Pixels: Towards Fine-Grained Medical Vision-Language Models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026. [ scholar ]
  4. Yehui Yang, Dalu Yang, Wenshuo Zhou, Fangxin Shang, Yifan Liu, Jie Ren, Haojun Fei, Qing Yang, Tao Chen. FCMBench: A Comprehensive Financial Credit Multimodal Benchmark for Real-world Applications. arXiv preprint arXiv:2601.00150, 2026. [ arXiv ] [ GitHub ] [ HuggingFace ]

2025

  1. Xiaoshuang Huang, Lingdong Shen, Jia Liu, Fangxin Shang, Hongxiang Li, Haifeng Huang, Yehui Yang. Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine. Proceedings of the AAAI Conference on Artificial Intelligence, 39(4), 3779-3787, 2025. [ arXiv ] [ GitHub ] [ HuggingFace ] [ scholar ]
  2. Fangxin Shang, Yuan Xia, Dalu Yang, Yahui Wang, Binglin Yang. MedRepBench: A Comprehensive Benchmark for Medical Report Interpretation. European Conference on Computer Vision (ECCV), 2026. arXiv:2508.16674. [ arXiv ] [ HuggingFace ]

2024

  1. Xiaoshuang Huang, Haifeng Huang, Lingdong Shen, Yehui Yang, Fangxin Shang, Junwei Liu, Jia Liu. A Refer-and-Ground Multimodal Large Language Model for Biomedicine. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2024. [ arXiv ] [ GitHub ] [ scholar ]
  2. Lingdong Shen, Fangxin Shang, Yehui Yang, Xiaoshuang Huang, Shiming Xiang. SegICL: A Universal In-context Learning Framework for Enhanced Segmentation in Medical Imaging. arXiv preprint arXiv:2403.16578, 2024. [ arXiv ]
  3. Jiale Peng, Yiran Jiang, Fangxin Shang, Zhongpeng Yang, Yuhan Qi, Siting Chen, Yehui Yang, RuoPing Jiang. Changes in masseter muscle morphology after surgical-orthodontic treatment in patients with skeletal Class III malocclusion with mandibular asymmetry: The automatic masseter muscle segmentation model. American Journal of Orthodontics and Dentofacial Orthopedics, 165(6), 638-651, 2024.
  4. Jiale Peng, Siting Chen, Fangxin Shang, Yehui Yang, RuoPing Jiang. Measurement Plane of the Cross-sectional Area of the Masseter Muscle in Patients with Skeletal Class III Malocclusion: An Artificial Intelligence Model. American Journal of Orthodontics and Dentofacial Orthopedics, 166(2), 112-124, 2024.

2023

  1. Fangxin Shang, Jie Fu, Yehui Yang, Haifeng Huang, Junwei Liu, Lei Ma. SynFundus-1M: A High-quality Million-scale Synthetic Fundus Images Dataset with Fifteen Types of Annotation. arXiv preprint arXiv:2312.00377, 2023. [ arXiv ] [ GitHub ]
  2. Haojun Fei, Qianqian Wang, Fangxin Shang, Wenshuo Xu, Xiaoshuang Chen, Yali Chen, Haifeng Li. HC-Net: A Hybrid Convolutional Network for Non-human Primate Brain Extraction. Frontiers in Computational Neuroscience, 17, 1113381, 2023.

2022

  1. Junde Wu, Huihui Fang, Fangxin Shang, Dalu Yang, Zhen Wang, Jian Gao, Yehui Yang, Yanwu Xu. SeATrans: Learning Segmentation-Assisted Diagnosis Model via Transformer. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2022. [ arXiv ] [ scholar ]
  2. Junde Wu, Huihui Fang, Zhen Wang, Dalu Yang, Yehui Yang, Fangxin Shang, Wenshuo Zhou, Yanwu Xu. Learning Self-calibrated Optic Disc and Cup Segmentation from Multi-rater Annotations. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2022. [ arXiv ]
  3. Yiran Jiang, Fangxin Shang, Jiale Peng, Jie Liang, Yifan Fan, Zhongpeng Yang, Yuhan Qi, Yehui Yang, Tao Xu, et al. Automatic Masseter Muscle Accurate Segmentation from CBCT Using Deep Learning-Based Model. Journal of Clinical Medicine, 12(1), 55, 2022.
  4. Fangxin Shang, Siqi Wang, Xiaorong Wang, Yehui Yang. An Effective Transformer-based Solution for RSNA Intracranial Hemorrhage Detection Competition. arXiv preprint arXiv:2205.07556, 2022. [ arXiv ]
  5. Junde Wu, Huihui Fang, Dalu Yang, Zhaowei Wang, Wenshuo Zhou, Fangxin Shang, Yehui Yang, Yanwu Xu. Opinions Vary? Diagnosis First! International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2022. [ arXiv ]
  6. Fangxin Shang, Yehui Yang, Dalu Yang, Junde Wu, Xiaorong Wang, Yanwu Xu. One Hyper-Initializer for All Network Architectures in Medical Image Analysis. arXiv preprint arXiv:2206.03661, 2022. [ arXiv ]

2021

  1. Yehui Yang*, Fangxin Shang*, Binghong Wu, Dalu Yang, Lei Wang, Yanwu Xu, Wensheng Zhang, Tianzhu Zhang. Robust Collaborative Learning of Patch-level and Image-level Annotations for Diabetic Retinopathy Grading from Fundus Image. IEEE Transactions on Cybernetics, 52(11), 11407-11417, 2021. (*equal contribution) [ arXiv ] [ GitHub ] [ scholar ]
  2. Huihui Fang, Fangxin Shang, Huazhu Fu, Fei Li, Xiaoguang Zhang, Yanwu Xu. Multi-modality Images Analysis: A Baseline for Glaucoma Grading via Deep Learning. International Workshop on Ophthalmic Medical Image Analysis, 139-147, 2021.

Experience

Patents & Community

30 granted invention patents, including 21 as first inventor.

Selected Granted Patents

  1. Fangxin Shang, Yehui Yang, Xiaoya Dai, Haifeng Huang. Image Desensitization Method, Model Training Method, Apparatus, Device, and Storage Medium. Chinese Invention Patent CN116228896B, granted 2025. [ patent ]
  2. Fangxin Shang, Yehui Yang, Xiaoya Dai. Medical Image Generation Method, Model Training Method, Apparatus, Device, and Medium. Chinese Invention Patent CN116402913B, granted 2024. [ patent ]
  3. Fangxin Shang, Yehui Yang, Xiaorong Wang, Haifeng Huang. Image Registration Method, Image Registration Model Training Method, and Apparatus. Chinese Invention Patent CN115908515B, granted 2024. [ patent ]
  4. Fangxin Shang, Yehui Yang, Qian Li, Haifeng Huang, Lei Wang. Method and Apparatus for Generating Convolutional Neural Networks, and Image Recognition Method and Apparatus. Chinese Invention Patent CN113361693B, granted 2022. [ patent ]
  5. Fangxin Shang, Yehui Yang, Haifeng Huang, Lei Wang. Semantic Segmentation and Model Training Methods, Apparatuses, Device, and Storage Medium. Chinese Invention Patent CN113920314B, granted 2022. [ patent ]

Community