GitHub

Typing SVG

🌐 Explore my full homepage →

🎓 Ph.D. Student in Engineering Science @ Harvard University 🧠 Building intelligent diagnostic agents | Multi-modal + Multi-task + LLMs 📧 Email: xiaolongluo[@]g.harvard.edu


profile views


🔬 Research Interests

Flexible Diagnostic Models with Multi-task and Multi-modal Learning
I work on developing advanced AI models that can simultaneously handle multiple diagnostic tasks while effectively integrating various types of medical data (imaging, clinical notes, lab results) to provide more comprehensive and accurate medical assessments.

Evaluating and Enhancing LLM Reasoning in Real-World Medical Settings
I work on developing evaluation frameworks and benchmarks to assess and improve how large language models reason over complex, temporally extended medical data. My goal is to enhance their fidelity, calibration, and robustness, ultimately enabling trustworthy and generalizable clinical AI systems.


🌱 Long-term Vision

I aspire to become a compound talent who deeply understands large-scale medical data, multi-modal learning, and end-to-end clinical applications. My long-term goal is to bridge cutting-edge AI research and real-world healthcare impact, driving both technical innovation and product commercialization. Ultimately, I hope to promote a more equitable distribution of medical resources, enabling better healthcare access and outcomes for all, and bringing broader benefits to society.


👨🏻‍💻 Languages and Tools

Python & Related VS Code Python Pandas OpenCV PyTorch TensorFlow scikit-learn Seaborn
Languages C C++ JavaScript TypeScript HTML5 CSS3 Bash MATLAB
Frameworks / Platforms / Tools React Vue.js Docker Git Linux Figma Photoshop

🤝 Connect with me

LinkedIn Google Scholar GitHub Xiaohongshu Instagram


✨ Quote

"Do, or do not. There is no 'try'." — Yoda

Read the original on github.com ↗