Alexander Pashevich

I am a Research Lead at RBC Borealis, where I develop advanced machine learning and deep learning solutions with enterprise-scale business impact. My work bridges research and applied AI, with contributions spanning predictive modeling, fraud detection, and pricing systems.

During my PhD at Inria/Université Grenoble Alpes, I pioneered robot learning research in the team and developed methods to enable robots to learn visually- and language-guided behaviors from data. In the five publications at top-tier conferences (ICCV, ICRA, IROS, NeurIPS), I showed advantages of deep learning approaches over classical control algorithms.

Beyond my research, I co-founded Vancouver AI Connect, a community that brings together researchers, practitioners, and industry leaders to foster collaboration and knowledge exchange in AI.

Email  /  Google Scholar  /  LinkedIn  /  Github  /  CV

My research interests include robotics, reinforcement and imitation learning, simulation-to-reality transfer, natural language processing, and vision-and-language navigation. More recently, I have been working on time-series forecasting research. During my Ph.D. studies, I was adviced by Cordelia Schmid and co-adviced by Ivan Laptev. I also had a pleasure to work with Chen Sun during my internship at Google Research.

A simple, inexpensive, theoretically motivated regularization term to enhance the robustness of deep time-index models for time-series forecasting.

A multimodal transformer-based architecture for vision-and-language navigation (VLN) improving results on a challenging task by 74%.

An approach learning to build shapes by disassembly that combines learning in low-dimensional state space and high-dimensional observation space.

A reinforcement learning approach to task planning that learns to combine primitive skills learned from demonstrations.

An approach for transferring policies learned in simulation to real-world robots by exploiting parallel computations.

A hierarchical reinforcement learning approach for learning from sparse rewards.

An algorithm for unsupervised extraction of piecewise planar models from depth data using constrained Gaussian mixture models.

website template credit