Haoran Lai

AI Researcher in Medical Vision and Multimodal Learning

I am a Ph.D. candidate in Biomedical Engineering at the University of Science and Technology of China (USTC), advised by Prof. Shaohua Zhou (IEEE Fellow, Dean). My research focuses on 3D medical vision-language models, cross-modal feature alignment, and clinical reasoning with reinforcement learning.

Previously, I completed my M.S. (2022) and B.S. (2019) in Biomedical Engineering at Southern Medical University, where I was advised by Prof. Meiyan Huang (Guangdong Young Pearl River Scholar).

Research Interests

• 3D Medical Vision-Language Models — CT/MRI report generation and abnormality reasoning
• Zero-shot & Few-shot Medical Diagnosis — cross-modal alignment for open-set evaluation
• Reinforcement Learning for Clinical Reasoning — consistency reward, chain-of-thought optimization
• Multimodal Alignment — explicit/implicit strategies bridging images and clinical text

News

• [Apr 2026] Honored as Outstanding Ph.D. Graduate of USTC (2026).
• [Apr 2026] Paper Med3D-R1 submitted to MICCAI 2026 (CCF B) — incentivizing clinical reasoning in 3D medical VLMs.
• [2025] Paper Bridged Semantic Alignment for Zero-shot 3D Medical Image Diagnosis accepted by IEEE Journal of Biomedical and Health Informatics (CAS Q1, JCR Q1 Top, IF: 6.8).
• [Dec 2024] Awarded the National Scholarship for Ph.D. Students at USTC.
• [Jun 2024] Presented CARZero as a poster at CVPR 2024 in Seattle, USA.
• [2024] Paper CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification published at CVPR 2024 (CCF A).

Selected Publications

Conference Papers

• CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification
  Haoran Lai, et al. CVPR 2024 (CCF A, Top Venue in Computer Vision)

• Long-Tailed Multi-Label Classification with Noisy Label of Thoracic Diseases from Chest X-Ray
  Haoran Lai, et al. ISBI 2024 (IEEE Flagship Conference in Biomedical Imaging)

Journal Papers

• Bridged Semantic Alignment for Zero-shot 3D Medical Image Diagnosis
  Haoran Lai, et al. IEEE Journal of Biomedical and Health Informatics, 2025. (CAS Q1, IF: 6.8)

• Prior Knowledge-Aware Fusion Network for Prediction of Macrovascular Invasion in Hepatocellular Carcinoma
  Haoran Lai, et al. IEEE Transactions on Medical Imaging, 2022. (CAS Q1, IF: 10.048)

• Multi-task Deep Learning Network to Predict Future Macrovascular Invasion in Hepatocellular Carcinoma
  Haoran Lai*, et al. EClinicalMedicine, 2021. (CAS Q1, IF: 17.033) (co-first author)

• Deep-Gated Recurrent Unit and Diet Network-Based Genome-Wide Association Analysis for Detecting the Biomarkers of Alzheimer’s Disease
  Medical Image Analysis, 2021. (CAS Q1, IF: 10.7) (2nd author)

Under Review

• E3D-GPT: Enhanced 3D Visual Foundation for Medical Vision-Language Model
  Haoran Lai, et al. (1st author)

• Med3D-R1: Incentivizing Clinical Reasoning in 3D Medical Vision-Language Models for Abnormality Diagnosis
  Haoran Lai, et al. MICCAI 2026 (under review, CCF B)

Honors & Awards

Contact

Feel free to reach out for collaborations on medical vision-language models, multimodal learning, or clinical AI.

• Email: haoranlai@mail.ustc.edu.cn
• GitHub: github.com/laihaoran
• Google Scholar: Profile