Eugene Lee

Researcher in Computer Vision and Vision-Language Reasoning with a focus on representation learning, token-efficient VLMs, and the evolution of LLMs through in-context learning and test-time adaptation.

Currently a Postdoctoral Researcher at the University of Cincinnati, my work bridges fundamental and applied AI. My fundamental research explores the mechanisms of in-context learning (ICL) and test-time adaptation (TTA) for LLMs to enhance model flexibility without retraining. On the applied side, I develop Vision-Language Models (VLMs) for biological applications, building imaging pipelines for organelle dynamics and utilizing LLMs to accelerate complex biological workflows through segmentation and temporal modeling.

Previously, I founded Paidge, an object-intelligence platform designed to index physical assets via scan-based conversational interaction. I led the development of a multi-frame aggregation model and a Perception Encoder with FAISS for efficient retrieval, integrated with a GraphRAG system for high-throughput indexing. The technology was successfully validated through multiple pilots with museums in the Greater Cincinnati area.

I earned my Ph.D. in Electronics Engineering from National Yang Ming Chiao Tung University (2023) under Prof. Chen-Yi Lee. My doctoral research focused on efficient deep learning, meta-learning, and resource-constrained neural networks, resulting in publications at top-tier venues including CVPR (Oral), ICCV, ECCV, and WACV.

Technical Expertise

• Core Research: In-context learning (ICL), Test-time adaptation (TTA), Multimodal reasoning, and Robust perception.
• Frameworks & Languages: PyTorch, Python, CUDA, C/C++, TypeScript, React.
• Infrastructure: AWS, Docker, iOS/Android deployment platforms.