Research
Research Interest
- Large Language Models (LLMs) for enterprise data management applications, particularly Text-to-SQL systems
- Stochastic optimization methods for machine learning, deep learning, and reinforcement learning
- Multi-agent reinforcement learning and robustness evaluation
- Federated learning and distributed optimization
Publications
2026
- Black-Box Uncertainty Quantification for Large Language Models via Ensemble-of-Ensembles.
AAAI 2026 Workshop on Assessing and Improving Reliability of Foundation Models in the Real World (AAAI 2026 Workshop).
W. Ma, D. Bhattacharjya, J. Lee, N. H. Pham, H. Kokel, Q. Ji.
2025
ConstrainedSQL: Training LLMs for Text2SQL via Constrained Reinforcement Learning.
NeurIPS 2025 Workshop on Efficient Reasoning (NeurIPS 2025 Workshop).
W. Chen, N. H. Pham, M. Glass, L. Vu, G. Rossiello, D. Subramanian, S. Paternain.Rationalization Models for Text-to-SQL.
ICLR 2025 Workshop on Reasoning and Planning for LLMs (ICLR 2025 Workshop).
G. Rossiello, N. H. Pham, M. Glass, J. Lee, D. Subramanian.The Consistency Hypothesis in Uncertainty Quantification for Large Language Models.
Forty-First Conference on Uncertainty in Artificial Intelligence (UAI 2025).
Q. Xiao, D. Bhattacharjya, B. Ganesan, R. Marinescu, K. Mirylenka, N. H. Pham, M. Glass, and J. Lee.
2023
- Evaluating Robustness of Cooperative MARL: A Model-based Approach.
2023 IEEE International Conference on Data Mining (ICDM).
N. H. Pham, L. M. Nguyen, J. Chen, H. T. Lam, S. Das, T. W. Weng.
2021
FedDR–Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimization.
The 35th Conference on Neural Information Processing Systems (NeurIPS 2021).
Q. Tran-Dinh, N. H. Pham, D. T. Phan, and L. M. Nguyen.Regression Optimization for System-level Production Control.
2021 American Control Conference (ACC).
D. T. Phan, L. M. Nguyen, P. Murali, N. H. Pham, H. Liu, J. Kalagnanam.A Hybrid Stochastic Optimization Framework for Composite Nonconvex Optimization.
Mathematical Programming.
Q. Tran-Dinh, N. H. Pham, D. T. Phan, and L. M. Nguyen.
2020
Stochastic Gauss-Newton Algorithms for Nonconvex Compositional Optimization.
The 37th International Conference on Machine Learning (ICML 2020).
Q. Tran-Dinh, N. H. Pham, and L. M. Nguyen.
[Python Code]ProxSARAH: An Efficient Algorithmic Framework for Stochastic Composite Nonconvex Optimization.
Journal of Machine Learning Research (JMLR).
N. H. Pham, L. M. Nguyen, D. T. Phan, and Q. Tran-Dinh.
[Python Code]A Hybrid Stochastic Policy Gradient Algorithm for Reinforcement Learning.
The 23rd International Conference on Artificial Intelligence and Statistics (AISTATS 2020).
N. H. Pham, L. M. Nguyen, D. T. Phan, P. H. Nguyen, M. van Dijk, and Q. Tran-Dinh.
[Python Code]
Earlier Work (2013–2018)
Automated Robotic Monitoring and Inspection of Steel Structures and Bridges.
Robotica.
H. M. La, T. H. Dinh, N. H. Pham, Q. P. Ha, and A. Q. Pham.Autonomous Robotic System using Non-Destructive Evaluation methods for Bridge Deck Inspection.
IEEE International Conference on Robotics and Automation (ICRA).
T. D. Le, S. Gibb, N. H. Pham, H. M. La, L. Falk, and T. Berendsen.Design and Implementation of an Autonomous Robot for Steel Bridge Inspection.
54th Annual Allerton Conference on Communication, Control, and Computing (Allerton).
N. H. Pham and H. M. La.Visual and 3D Mapping for Steel Bridge Inspection Using a Climbing Robot.
33rd International Symposium on Automation and Robotics in Construction and Mining (ISARC).
N. H. Pham, H. M. La, Q. P. Ha, S. N. Dang, A. H. Vo, and Q. H. Dinh.Quadrotor Helicopter: A Practical Design Approach.
IEICE International Conference on Integrated Circuits, Design and Verification (IEICE).
T.-D. D. Phan, N. H. Pham, K.-N. Le-Huu, and A.-V. D. Dinh.
Preprints
Convergence Rates of Accelerated Markov Gradient Descent with Applications in Reinforcement Learning.
arXiv:2002.02873.
T. T. Doan, L. M. Nguyen, N. H. Pham, and J. Romberg.Finite-Time Analysis of Stochastic Gradient Descent under Markov Randomness.
arXiv:2003.10973.
T. T. Doan, L. M. Nguyen, N. H. Pham, and J. Romberg.