About Me

Since August 2020, I have been pursuing a Ph.D. in Computer Science at The Ohio State University under the expert guidance of Prof. Rajiv Ramnath. My research focuses on Large Language Models (LLMs), Vision-Language Models (VLMs), Time Series Analysis, and Multimodal Systems, with a strong emphasis on bridging vision and language understanding and document processing. My work has been recognized at prestigious conferences such as ICML and SIGKDD.

In May 2022, I joined Flairsoft as a Senior Machine Learning Scientist, where I’ve developed advanced solutions, including risk analysis models, speech-to-text systems, and document annotation tools. Combining academic research with practical applications, I am committed to leveraging cutting-edge technologies to solve real-world challenges and drive innovation.

I am actively seeking opportunities in Machine Learning and AI!

Research

I am broadly interested in the fields of Machine Learning, Large Language Models (LLMs), Vision-Language Models (VLMs), Multimodal Systems, and Time Series Analysis. My research explores innovative ways to bridge vision and language understanding, focusing on document processing and predictive modeling. Some of my past papers are as follows:

• Multimodal:

  • DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness. Submitted in CVPR, 2024.

  • DocParseNet: Advanced Semantic Segmentation and OCR Embeddings for Efficient Scanned Document Annotation. Published in ICML, 2024

  • CrashFormer: A Multimodal Architecture to Predict the Risk of Crash. Published in Proceedings of the 1st ACM SIGSPATIAL International Workshop on Advances in Urban-AI, 2023.

• Time Series:

  • DSSRNN: Decomposition-Enhanced State-Space Recurrent Neural Network for Time-Series Analysis. Submitted in KDD 2025.

  • Novel Physics-Based Machine-Learning Models for Indoor Air Quality Approximations. Published in The 9th SIGKDD International Workshop on Mining and Learning from Time Series, 2023.

  • Predicting Airborne Pollutant Concentrations and Events in a Commercial Building Using Low-Cost Pollutant Sensors and Machine Learning: A Case Study. Published in Building and Environment, 2022.

Contact

• Email: mohammadshirazi.2[at]osu[dot]edu