I am a Multimodal Large Model Algorithm Engineer. I am eager to contribute to research in areas such as, but not limited to:

• Multi-modal Large Language Model (MLLM)
• Visual Comprehension
• Mixture of Experts
• The Application of MLLM

I welcome academic discussions or collaborations. Please feel free to email me if interested.

🔥 News

• 2025.07:   Joined Xiaohongshu (RedNote) as a Multimodal Large Model Algorithm Engineer.
• 2024.12:   One paper is accepted to AAAI 2025 (CCF-A).
• 2024.12:   Got Chinese National Scholarship.
• 2024.12:   One paper is accepted to IEEE TMI (Top journal, IF=11.3).
• 2023.11:   Got Master’s First-Class Academic Scholarship.
• 2024.05:   Two paper are accepted to MICCAI 2023 (CCF-B).
• 2023.12:   One paper is accepted to BIBM 2023 (CCF-B).
• 2023.11:   Got Master’s First-Class Academic Scholarship.
• 2023.07:   One paper is accepted to ICANN 2023 (CCF-C).
• 2022.03:   Got Outstanding Graduates of Sichuan Province.

🧑‍💻 Work Experience 🧑‍💻

• 2025.07 - Present: Multimodal Large Model Algorithm Engineer, 【Xiaohongshu (RedNote)】, 📍Shanghai, China.

📝 Selected Publications

See the full list at Google Scholar.

AAAI2025

MedPLIB: Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine

Xiaoshuang Huang, Lingdong Shen, Jia Liu, Fangxin Shang, Hongxiang Li, Haifeng Huang, Yehui Yang

Paper, Code

The 39th Annual AAAI Conference on Artificial Intelligence (AAAI), 2025.

TMI

Cross-Modal Conditioned Reconstruction for Language-guided Medical Image Segmentation

Xiaoshuang Huang, Hongxiang Li, Meng Cao, Long Chen, Chenyu You, Dong An

Paper, Code

IEEE Transactions on Medical Imaging (TMI), 2024. (IF=11.3)

MICCAI2024

A Refer-and-Ground Multimodal Large Language Model for Biomedicine

Xiaoshuang Huang, Haifeng Huang, Lingdong Shen, Yehui Yang, Fangxin Shang, Junwei Liu, Jia Liu

Paper, Code

International conference on medical image computing and computer-assisted intervention (MICCAI), 2024. (Top Conference in Medical Image Processing, CCF-B.)

Under Review

SegICL: A Universal In-context Learning Framework for Enhanced Segmentation in Medical Image

Lingdong Shen, Fangxin Shang, Xiaoshuang Huang, Yehui Yang, Haifeng Huang, Shiming Xiang

Paper

Under Review.

BIBM2023

Polyp2Former: Boundary Guided Network Based on Transformer for Polyp Segmentation

Xiaoshuang Huang, Jinze Huang, Shuo Wang, Yaoguang Wei, Dong An, Jincun Liu

Paper

IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2023. (CCF-B.)

ICANN2023

E-Patcher: A Patch-Based Efficient Network for Fast Whole Slide Images Segmentation

Xiaoshuang Huang, Shuo Wang, Jinze Huang, Yaoguang Wei, Xinhua Dai, Yang Zhao, Dong An, Xiang Fang

Paper

International Conference on Artificial Neural Networks (ICANN), 2023. (CCF-C.)

💻 Internships

• 2025.03 - 2025.07: Xiaohongshu, Beijing, China.
• 2024.01 - 2024.08: Baidu, Beijing, China.
• 2022.02 - 2022.09: SenseTime, Shanghai, China.

🎖 Honors and Awards

• 2024 National Scholarship.
• 2024 Master’s First-Class Academic Scholarship.
• 2023 Master’s First-Class Academic Scholarship.
• 2022 Master’s Second-Class Academic Scholarship.
• 2022 Outstanding Graduates of Sichuan Province.
• 2021 Chen Yuxin First-Class Scholarship (1/1600) 2021.
• 2020 National Encouragement Scholarship.
• 2019 National Encouragement Scholarship.

Patents

• Chinese invention patent: Training method, inference method, device, apparatus and storage medium for large language model. (The first inventor, Publication No.: CN118673325A)