About Me
I am a GenAI Researcher at KX, where I work on machine learning and generative AI for financial applications, with a focus on intelligent agents, sequential decision-making, and modeling complex financial systems. I earned my Ph.D. in Electrical and Computer Engineering from McGill University, with affiliations to Mila (Quebec AI Institute), the Centre for Intelligent Machines (CIM), and the International Laboratory on Learning Systems (ILLS).
Affiliations
Research Interests
My research lies at the intersection of sequential decision-making, dynamical systems, and generative modeling. I study multi-agent reinforcement learning, decentralized learning, shared autonomy, and time-series modeling, with an emphasis on coordination, adaptation, and learning in complex dynamical environments. I am also interested in large language models and diffusion models, particularly in understanding and improving how generative systems learn, interact, and scale.
Time-Series Forecasting
Temporal modeling and multi-step prediction of dynamical systems, with forecasts updated as new observations arrive.
Multi-Agent Reinforcement Learning
Cooperative sequential decision-making with a shared reward.
Large Language Models
Attention-based sequence modeling, retrieval-augmented generation, and reinforcement learning for tool use.
Diffusion Models
Generative modeling through iterative denoising, including decentralized training for image and video synthesis.
Education
Master of Engineering
McGill University 2017-2019
Thesis: Learning in the presence of partial observability and concept drifts. Supervisor: Aditya Mahajan.
Bachelor of Science
Islamic University of Technology(IUT) 2011-2015
Thesis: Classification of Benign and Malignant Tissue with Logistic Regression using Dynamic Sigmoid Function .Awards and Honors
- McGill Engineering Doctoral Award(MEDA) (2019-2022).
- GERAD co-supervised student award (2019).
- Mitacs Accelerate Fellowship (2018).
- Recepient of Graduate Excellence Fellowship at McGill (2017,2018,2021).
- Member of the winning team of Brac Manthan Award for e health catagory (2016).
- OIC scholarship (for academic excellence in university entrance examination) (2011).
- Recipient of the Daily Star Award for academic excellence in O and A levels (2011).
Selected Publications
- Raihan Seraj, Jivitesh Sharma and Ole-Christoffer Granmo. "Tsetlin Machine for Solving Contextual Bandit Problems". In 36th Conference on Neural Information Processing Systems (NeurIPS). [pdf]
- Zhiying Jiang, Raihan Seraj, Marcos Villagra, Bidhan Roy. “Heterogeneous Decentralized Diffusion Models.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. (CVPR) 2026. [pdf]
- Raihan Seraj, Jerome Le Ny, Aditya Mahajan. "Fatigue and Task Load Dependent Decision Referrals for Joint Binary Classification in Human-Automation Teams", IEEE Control Systems Letters.[pdf]
- Raihan Seraj, Aditya Mahajan, Jerome Le Ny. "Dynamic Estimation of Mental Workload and Operator Accuracy for Time-Constrained Binary Classification Tasks", IEEE Transactions of Human Machine Systems.[pdf]
- Anurag Koul, Shivakanth Sujit, Shaoru Chen, Ben Evans, Lili Wu, Byron Xu, Rajan Chari, Riashat Islam, Raihan Seraj, Yonathan Efroni, Lekan P Molu, Miroslav Dudík, John Langford, Alex Lamb. "PcLast: Discovering Plannable Continuous Latent States". In Proceedings of the 41st International Conference on Machine Learning (ICML), Vienna, Austria, 2024.[pdf]
- Qi Yan, Raihan Seraj, Jiawei He, Lili Meng, Tristan Sylvain. "Autocast++: Enhancing world event prediction with zero-shot ranking-based context retrieval". In International Conference on Learning Representation (ICLR), 2024.[pdf]
- Raihan Seraj, Jerome Le Ny and Aditya Mahajan "Mean-field approximation for large-population beauty-contest games". In 2021 IEEE 60th Conference on Decision and Control (CDC).[pdf]
- Jayakumar Subramanian, Amit Sinha, Raihan Seraj and Aditya Mahajan. "Approximate information state for approximate planning and reinforcement learning in partially observed systems." Journal of Machine Learning Research (JMLR).[pdf]
- Jayakumar Subramanian, Raihan Seraj and Aditya Mahajan ”Reinforcement learning for mean-field teams” AAMAS Workshop on Adaptive and Learning Agents, Montreal, Canada, 13-17 May, 2019. [pdf]
- Riashat Islam, Raihan Seraj, Pierre-Luc Bacon, Doina Precup. “Entropy Regularization with Discounted Future State Distribution in Policy Gradient Methods”, NeurIPS 2019 workshop on Optimization Foundations for Reinforcement Learning. [pdf]
- Riashat Islam, Raihan Seraj, Samin Yeasar Arnob, Doina Precup. “Doubly Robust Off-Policy Actor Critic Algorithms for Reinforcement Learning”, NeurIPS 2019 workshop on Safety and Robustness in Decision Making. [pdf]
- Raihan Seraj, Mohiuddin Ahmed ”Concept drifts for big data”, Combating Security Challenges in the Age of Big Data - Powered by State-of-theArt Artificial Intelligence Techniques, Springer.[pdf]
- Ahmed, Mohiuddin, Raihan Seraj, and Syed Mohammed Shamsul Islam. "The k-means algorithm: A comprehensive survey and performance evaluation." Electronics 9.8 (2020): 1295.[pdf]
News
- 24-March-2026 Joined KX as Gen AI Researcher. Excited to work on AI in capital markets
- 10-March-2026 Paper titled "Efficient Decentralized Diffusion with Heterogeneous Training Objectives" got accepted at CVPR 2026.
- 13-July-2025 Paper titled "Dynamic Estimation of Mental Workload and Operator Accuracy for Time-Constrained Binary Classification Tasks" got accepted at IEEE Transactions on Human-Machine Systems (THMS)
- 3-June-2025 Joined Bagel Labs as a Machine Learning Scientist. Excited to work on distributed reinforcement learning
- 2-June-2025 Paper titled "Fatigue and task load dependent decision referrals for joint binary classification in human-automation teams" accepted at IEEE-LCSS
- 29-May-2025 Obtained my unfoldable and fragile PhD diploma from McGill University. Congratulations to class of 2025
- 21-March-2025 I have successfully defended my PhD thesis
- 05-June-2024 I have successfully completed my PhD research seminar examination.
- 14-Sep-2022 Paper titled "Tsetlin Machine for Solving Contextual Bandit Problems" got accepted at Neural Information Processing Systems (NeurIPS) 2022.
- 9-Sept-2021 Successfully completed my PhD thesis proposal examination.
- 1-Jul-2021 Joined Valence Drug Discovery for Scientist in Residence Program.
- 27-Jul-2021 Paper titled "Mean-field approximation for large-population beauty-contest games" got accepted at IEEE Conference on Decision and Control (CDC) 2021.
- 1-Aug-2021 Paper titled "Approximate information state for approximate planning and reinforcement learning" got accepted at Journal of Machine Learning Research (JMLR).
- 24-Feb-2020 Successfully completed my PhD comprehensive examination.
- 1-Jan-2019 Started my PhD at the department of Electrical and Computer Engineering.
- 31-Dec-2018 Successfully completed my Masters degree from the department of Electrical and Computer Engineering.
- 1-Mar-2018 Joined Aerial Technologies as a Research Scientist Intern.
- 1-Jan-2017 Started graduate school at the department of Electrical and Computer Engineering, McGill Univeristy.
- 31-Dec-2015 Started a job as a Research Engineer at the Department of Biomedical Physics and Technology, University of Dhaka.
- 25-Dec-2015 Graduated with first class honors from the department of Electrical and Electronic Engineering, Islamic University of Technology.