AURELIS research outputs include peer-reviewed publications, software and research artifacts, datasets and benchmarks, and other resources developed through the lab's research activities.
Selected publications reflecting AURELIS research areas, student-led research, and ongoing scholarly collaborations are highlighted below.
Benyamin Ahmadnia, Shazan Mohammed, Sahar Hooshmand, and Li Zhou. "Large Language Model-Based Automatic Post-Editing for Test-Time Domain Adaptation in Neural Machine Translation." 9th International Conference on Artificial Intelligence (ICAI 2026) - Orlando, USA.
Benyamin Ahmadnia, Yeswanth Soma, Marsa Rayani, and Sahar Hooshmand. "Leveraging Large Language Models for Superior Low-Resource Neural Machine Translation." 2025 IEEE 8th Congress on Information Science and Technology (CiSt) - Marrakesh, Morocco.
Benyamin Ahmadnia, Yeswanth Soma, and Hossein Sarrafzadeh. "Multilingual Pre-training Meets Supervised Neural Machine Translation: A Reproducible Evaluation on English-French and Finnish Translation." 15th International Conference on Recent Advances in Natural Language Processing (RANLP 2025) - Varna, Bulgaria.
Benyamin Ahmadnia, Sumaiya Shaikh, Bibek Poudel, Shazan Mohammed, and Sahar Hooshmand. "Advancing Clinical Translation in Nepali through Fine-Tuned Multilingual Models." 15th International Conference on Recent Advances in Natural Language Processing (RANLP 2025) - Varna, Bulgaria.
Anjana Krishnamoorthy, Kartik Ivaturi, and Benyamin Ahmadnia. "Multi-Agent Reinforcement Learning for Interactive Code Debugging with Human Feedback and Memory." 15th International Conference on Recent Advances in Natural Language Processing (RANLP 2025) - Varna, Bulgaria.
Lucas Norpchen, Omar Garcia, Koby Winkler, Jose Temblador, and Benyamin Ahmadnia. "A Lightweight Machine Learning Pipeline for Crypto Forecasting: A Capstone Case Study in Software Engineering Education." 1st International Conference on Software Engineering of Emerging Technologies (SEET 2025) - Long Beach, USA.
Software, code repositories, experimental resources, and other research artifacts associated with AURELIS projects will be made available here as they are released publicly.
For Dr. Ahmadnia's complete publication record, please visit the Publications page.