About
I am a machine learning researcher working on multimodal AI, large language models, and real-world deployment of vision–language systems. I currently live and work in South Korea.
My interests include multimodal representation learning, evaluation and robustness of video understanding systems, and practical MLOps for large-scale inference.
Research & Publications
I am in the process of organizing my publications and projects. A detailed list (with PDFs and code) will appear here soon.
- Google Scholar profile (link coming soon)
- Selected preprints and patents
- Slides and talk materials
Projects
I work on applied multimodal systems, including video search and summarization pipelines, evaluation frameworks, and large-scale embedding workflows.
- Video Search & Summarization (VSS) – large-scale video understanding stack
- Multimodal LLM fine-tuning for safety and content classification
- Tools for reading and analyzing research papers more efficiently
Contact
The easiest way to reach me is by email. I’m open to discussions about research collaboration, postdoctoral opportunities, and applied ML projects.
Email: ahmadmobeen24@gmail.com
I will soon link my GitHub, Google Scholar, and YouTube channel here.