KV

KONG Vungsovanreach

PhD Candidate
Computer Vision | LLM | VLM | Applied AI
Google Scholar Profile ORCID Profile LinkedIn Profile

About

PhD candidate specializing in applied computer vision and multimodal AI, with over 8 years in software development and 5+ years in ML/AI. His research focuses on integrating Large Language Models (LLMs) with visual data for real-world applications in safety, healthcare, and surveillance.

Professional Experience

Research Focus

Technical Expertise

Strong proficiency in Python and C++ with extensive experience in computer vision libraries and LLM frameworks. Skilled in using deep learning frameworks for developing advanced image and video analysis systems.

Research Goals

Bridging vision-language AI and big data to develop scalable, impactful solutions for safety and compliance across industries. Focus on generating descriptive insights from visual patterns and creating systems that can understand and interpret complex visual information in real-world contexts.

Key Contributions