PNNL

Sai Munikoti is a data scientist at Pacific Northwest National Laboratory focusing on artificial intelligence (AI) and machine learning. His work primarily involves the development and application of multimodal large language models. His projects include STEEL THREAD and EXPERT 2.0 (fiscal year 2023) to advance the U.S. Department of Energy National Nuclear Security Administration’s nonproliferation mission via trustworthy AI reasoning models and PolicyAI and WindAI to develop generative AI capability for streamlining and improving federal permitting and siting operations. He has published in multiple journals and conference proceedings, including the Association for the Advancement of Artificial Intelligence and Knowledge Discovery in Databases Scholar. Sai received his PhD in electrical and computer engineering from Kansas State University in 2022. In addition to his doctorate, Sai also holds an MS from the Indian Institute of Technology Gandhinagar and a BE from the Birla Institute of Technology Sindri.

• Large language models
• Multimodal models
• Knowledge graphs

• AI
• Data science
• Deep learning
• High performance computing
• Machine learning
• Natural language processing
• Reinforcement learning

• PhD in electrical and computer engineering, Kansas State University
• MS in electrical engineering, Indian Institute of Technology Gandhinagar
• BS in electrical engineering, Birla Institute of Technology Sindri

2024

• Munikoti S., I. Stewart, S. Horawalavithana, H. Kvinge, T. Emerson, S.E. Thompson, and K. Pazdernik. 2024. "Generalist Multimodal AI: A Review of Architectures, Challenges and Opportunities." arXiv preprint arXiv:2406.05496
• Munikoti S., B. Natarajan, and M. Halappanavar. 2024. "GraMeR: Graph meta reinforcement learning for multi-objective influence maximization." Journal of Parallel and Distributed Computing 192, 104900. doi:10.1016/j.jpdc.2024.104900

2023

• Das L., S. Munikoti, and M. Halappanavar. 2023. "There is more to graphs than meets the eye: Learning universal features with self-supervision." arXiv preprint arXiv:2305.19871
• Horawalavithana S., S. Munikoti, I. Stewart, and H. Kvinge. 2023. "Scitune: Aligning large language models with scientific multimodal instructions." arXiv preprint arXiv:2307.01139
• Munikoti S., A. Acharya, S. Wagle, and S. Horawalavithana. 2023. "ATLANTIC: Structure-Aware Retrieval-Augmented Language Model for Interdisciplinary Science." Workshop on AI to Accelerate Science and Engineering, The Thirty-Eighth Annual AAAI Conference on Artificial Intelligence. arXiv preprint arXiv:2311.12289
• Munikoti S., A. Acharya, S. Wagle, and S. Horawalavithana. 2023. "Evaluating the Effectiveness of Retrieval-Augmented Large Language Models in Scientific Document Reasoning." Proceedings of the 4th Workshop on Scholarly Document Processing @ ACL 2024. arXiv preprint arXiv:2311.04348
• Munikoti S., D. Agarwal, L. Das, M. Halappanavar, and B. Natarajan. 2023. "Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive Review of Algorithms and Applications." IEEE Transactions on Neural Networks and Learning Systems. PNNL-SA-174409. doi:10.1109/TNNLS.2023.3283523
• Tharzeen A., S. Munikoti, P. Prakash, J. Kim, and B. Natarajan. 2023. "A General Spatiotemporal Imputation Framework for Missing Sensor Data." In IEEE Conference on Artificial Intelligence (CAI 2023) 55–58. Santa Clara, CA, June 5–6, 2023. Los Alamitos, California: IEEE Computer Society. PNNL-SA-183063. doi:10.1109/CAI54212.2023.00032
• Wagle S., S. Munikoti, A. Acharya, S. Smith, and S. Horawalavithana. 2023. "Empirical evaluation of uncertainty quantification in retrieval-augmented language models for science." Workshop on Scientific Document Understanding, The Thirty-Eighth Annual AAAI Conference on Artificial Intelligence. arXiv preprint arXiv:2311.09358