jiajun.deFine-Tuning Qwen2.5-VL on Your Own Images using LLaMA-FactoryThe world of Large Language Models (LLMs) is evolving rapidly into Vision-Language Models (VLMs). Models that can see and understand images—like Qwen2.5-VL—are game changers for tasks like OCR, medical imaging analysis, and visual agents. However, fi...Feb 13·4 min read
jiajun.deThe Ultimate Beginner’s Guide to FAU HPC: From Zero to A100So, you’ve received an invitation to use the High-Performance Computing (HPC) cluster at FAU (likely a Tier3 project). You want to run Deep Learning, VLM, or RL experiments, but you are staring at a black terminal screen and don't know where to start...Feb 12·5 min read
jiajun.deExplainable Radiologist-Aligned VLM for CT Image Quality AssessmentAuthors: Jiajun Wang, Yipeng Sun, Siming Bayer, Andreas MaierAffiliation: Pattern Recognition Lab, Friedrich-Alexander Universität Erlangen-Nürnberg, GermanyLinks: GitHub Repository 📖 Abstract The assessment of computed tomography (CT) image qualit...Dec 19, 2025·4 min read
jiajun.deMy personal experiences and introductionHi, I am Jiajun Wang(Jesse as my nickname). I am currently a Master's student at FAU Erlangen-Nürnberg, combining a solid Engineering foundation with cutting-edge AI research. Engineering Background: Dec 8, 2025·3 min read