I am a Member of Technical Staff at Microsoft AI (MAI), working on the final climb post-training of the MAI-Thinking Vision Language Model. Previously, I was a Senior Research Scientist at Microsoft Research AI Frontiers, where I was a core member of the Phi-series models — contributing to pre-training with compact world models and building out the RL post-training stack.
I completed my PhD in Machine Learning at Mila – Quebec AI Institute and McGill University, supervised by Doina Precup and Joelle Pineau, with Yoshua Bengio and John Langford as co-advisors. My thesis was on Latent State Discovery for Robust, Reusable and Reliable Deep RL.
Research Interests: I build reasoning models and systems for math, coding and vision tasks, with a focus on long horizon agentic AI, world dynamics models, latent representation learning, goal-directed planning and exploration capabilities. My recent work focuses on Language Model pre-training, thinking in the latent space with faster rollout capabilities; self-verification, curriculum learning, scalable RL post-training recipe and improving long horizon reasoning. I care about reliable and reproducible AI, ensuring robustness of large scale AI systems.
Industry Research Experience
- Microsoft AI (MAI), New York — Aug 2026 – Present Member of Technical Staff — RL Post-Training | Final Climb Vision-Language Models Collaborators: Ali Farhadi, John Langford, Ranjay Krishna
- Microsoft Research AI Frontiers, New York — Jan 2025 – Present Senior Research Scientist — RL Post-Training | Pre-Training | World Models Collaborators: John Langford, Alex Lamb, Kwangjun Ahn, Tim Pearce, Manan Tomar
- SDAIA, HUMAIN, Riyadh — Jul 2024 – Jan 2025 Senior Research Scientist — Post-Training and Safety Alignment Collaborators: M Saiful Bari, Sheikh Jubair, Ehsan Hoque, Pedro Moreno
- DreamFold AI, Montreal — Jun 2023 – Jul 2024 Research Scientist — RL & Flow Matching for Protein Structure Design Collaborators: Alex Tong, Joey Bose, Jarrid Rector-Brooks
- Microsoft Research, Montreal — Apr 2022 – Apr 2023 Student Researcher — Factorized Latent Representations in RL Collaborators: R. Tachet des Combes, R. Laroche, H. van Seijen, A. Lamb, J. Langford, D. Misra, A. Krishnamurthy
- Apple MLR, San Jose — Jan 2022 – Apr 2022 Research Scientist Intern — Representation Learning for World Models in RL Collaborators: Devon Hjelm, Samy Bengio
- Microsoft Research, New York — Apr 2021 – Dec 2021 Research Scientist Intern — Provable RL for Latent State Discovery Collaborators: Alex Lamb, John Langford, Akshay Krishnamurthy, Dylan Foster, Yonathan Efroni, Dipendra Misra
Academic Research Experience
- Microsoft Research, Montreal — Jun 2017 – May 2019 Student Researcher Intern — Reproducibility in Deep RL, Active Imitation Learning Collaborators: Phillip Bachman, Alessandro Sordoni, John Langford
- Caltech and NASA JPL — Jun – Aug 2015 Improved State Estimation for a Resilient Spacecraft Executive Supervisors: R. Murray, C. McGhan (SURF Program)
- University of Cambridge — Mar – Sep 2016 Active Learning for Images using Bayesian Deep Learning Uncertainty Supervisors: Z. Ghahramani, Y. Gal
- UCL — Sep 2015 – Mar 2016 Improving Convergence of Deterministic Policy Gradient Algorithms in RL Supervisors: J. Shawe-Taylor, G. Lever; and D. Silver
- Johns Hopkins University — Jun – Aug 2014 Cost-Sensitive Decision Tree of Classifiers for Medical Data Supervisor: Suchi Saria (SRE Program)
Education
- McGill University & Mila – Quebec AI Institute, Montreal — Sep 2017 – Sep 2022 PhD in Machine Learning Supervisors: Doina Precup, Joelle Pineau; Co-Advisors: Yoshua Bengio, John Langford. Thesis: Latent State Discovery for Robust, Reusable and Reliable Deep RL.
- University of Cambridge, St John's College — Sep 2015 – Aug 2016 MPhil, Machine Learning, Speech & Language Technology Supervisors: Zoubin Ghahramani, Yarin Gal. Thesis: Active Learning with Image Data using Bayesian Uncertainty in Deep Learning.
- University College London — Sep 2011 – Jul 2015 BEng, Electronic & Electrical Engineering (ML Major) Supervisors: John Shawe-Taylor, Guy Lever; Co-Advisor: David Silver. Thesis: Analysing Convergence of Deep Policy Optimization in RL; Deterministic Policy Gradient Methods.
Selected Publications
- Jayden Teoh, Manan Tomar, John Langford, Riashat Islam, et al. "Next-Latent Prediction Transformers Learn Compact World Models" — NeurIPS 2026
- Alesia Ivanova, Sumeet Ramesh Motwani, Riashat Islam, et al. "h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning" — ICML 2026 (Spotlight)
- Tejas Krishnan, Sumeet Ramesh Motwani, Riashat Islam, et al. "Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Non-Verifiable Domains" — ICML 2026
- Zeyu Wang, Yao-Hui Li, Xin Li, Hongyu Zang, Riashat Islam. "Learning Fused State Representations for Control from Multi-View Observations" — ICML 2025
- Guillaume Huguet, James Vuckovic, Riashat Islam, et al. "Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation" — NeurIPS 2024
- Ruixiang Sun, Hongyu Zang, Xin Li, Riashat Islam. "Learning Latent Dynamic Robust Representations for World Models" — ICML 2024
- Md Mofijul Islam, Alexi Gladstone, Riashat Islam, Tariq Iqbal. "EQA-MX: Embodied Question Answering using Multimodal Expression" — ICLR 2024 (Spotlight)
- Riashat Islam*, Manan Tomar*, et al. "Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information" — ICML 2023
- Manan Tomar, Riashat Islam, Matthew E. Taylor, Philip Bachman, Sergey Levine. "Ignorance is Bliss: Robust Control via Information Gating" — NeurIPS 2023
- Alex Lamb*, Riashat Islam*, et al. "Guaranteed Discovery of Controllable Latent States with Multi-Step Inverse Models" — TMLR 2023
- Riashat Islam, Hongyu Zang, et al. "Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning" — NeurIPS 2022
For a complete list of publications, see my Google Scholar profile.
Journals and Patents
- Alex Lamb*, Riashat Islam*, et al. "Guaranteed Discovery of Controllable Latent States." Patent: Under Submission with Microsoft Research
- Vincent Francois-Lavet, Peter Henderson, Riashat Islam, Marc G. Bellemare, Joelle Pineau. "An Introduction to Deep Reinforcement Learning." Foundations and Trends in Machine Learning, 2018