Publications

DSSRNN: Decomposition-Enhanced State-Space Recurrent Neural Network for Time-Series Analysis

Published in ICLM (submitted), 2025

DSSRNN is a cutting-edge time series forecasting model that combines decomposition techniques with state-space and recurrent neural networks to deliver exceptional accuracy and efficiency in environmental and broader analytical applications.

Recommended citation: Mohammadshirazi, A., Nosratifiroozsalari, A., & Ramnath, R. (2024). DSSRNN: Decomposition-Enhanced State-Space Recurrent Neural Network for Time-Series Analysis. arXiv preprint arXiv:2412.00994. https://arxiv.org/pdf/2412.00994

DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness

Published in CVPR (submitted), 2024

DLaVA enhances Document Visual Question Answering by integrating answer localization with advanced interpretability, ensuring precise and trustworthy results for complex document layouts.

Recommended citation: Mohammadshirazi, A., Neogi, PPG., Lim, S., & Ramnath, R. (2024). DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness. arXiv preprint arXiv:2412.00151. https://arxiv.org/pdf/2412.00151

DocParseNet: Advanced Semantic Segmentation and OCR Embeddings for Efficient Scanned Document Annotation

Published in ICML: Efficient Systems for Foundation Models (ES-FoMo II), 2024

DocParseNet combines semantic segmentation and OCR embeddings to deliver precise, efficient, and context-aware annotation of scanned documents.

Recommended citation: Mohammadshirazi, A., Nosratifiroozsalari, A., Zhou, Z., Kulshrestha, D., & Ramnath, R. (2024). DocParseNet: Advanced Semantic Segmentation and OCR Embeddings for Efficient Scanned Document Annotation. arXiv preprint arXiv:2406.17591. https://arxiv.org/pdf/2406.17591

CrashFormer: A Multimodal Architecture to Predict the Risk of Crash

Published in ACM SIGSPATIAL: Advances in Urban-AI, 2023

This paper introduces CrashFormer, a multi-modal predictive model leveraging diverse data to significantly enhance traffic accident prediction, thereby contributing to global public safety efforts.

Recommended citation: Karimi Monsefi, A., Shiri, P., Mohammadshirazi, A., Karimi Monsefi, N., Davies, R., Moosavi, S., & Ramnath, R. (2023, November). CrashFormer: A Multimodal Architecture to Predict the Risk of Crash. In Proceedings of the 1st ACM SIGSPATIAL International Workshop on Advances in Urban-AI (pp. 42-51). https://dl.acm.org/doi/abs/10.1145/3615900.3628769

Novel Physics-Based Machine-Learning Models for Indoor Air Quality Approximations

Published in 29TH ACM SIGKDD Conference On Knowledge Discovery And Data Mining: Mining and Learning from Time Series, 2023

This paper centers on enhancing indoor air quality predictions in commercial buildings through the innovative integration of low-cost sensors and advanced physics-based machine learning models.

Recommended citation: Mohammadshirazi, A., Nadafian, A., Monsefi, A. K., Rafiei, M. H., & Ramnath, R. (2023). Novel Physics-Based Machine-Learning Models for Indoor Air Quality Approximations. arXiv preprint arXiv:2308.01438. https://arxiv.org/abs/2308.01438

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

This paper focuses on predicting airborne pollutant concentrations in commercial buildings using innovative low-cost sensors and machine learning techniques.

Recommended citation: Mohammadshirazi, A., Kalkhorani, V. A., Humes, J., Speno, B., Rike, J., Ramnath, R., & Clark, J. D. (2022). Predicting airborne pollutant concentrations and events in a commercial building using low-cost pollutant sensors and machine learning: a case study. Building and Environment, 213, 108833. https://www.sciencedirect.com/science/article/pii/S0360132322000816

Ahmad Mohammadshirazi