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

profile photo
Research

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.

fast-texture DeepRRTime: Robust Time-series Forecasting with a Regularized INR Basis
Chandramouli Sastry, Mahdi Gilany, Yik Chau Lui, Martin Magill, Alexander Pashevich
Transactions on Machine Learning Research (TMLR), 2025
bibtex

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

fast-texture Episodic Transformer for Vision-and-Language Navigation
Alexander Pashevich, Cordelia Schmid, Chen Sun
ICCV, 2021
bibtex / code / website

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

fast-texture Learning visual policies for building 3D shape categories
Alexander Pashevich*, Igor Kalevatykh*, Ivan Laptev, Cordelia Schmid
IROS, 2020
bibtex / website / video

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

fast-texture Learning to combine primitive skills: A step towards versatile robotic manipulation
Robin Strudel*, Alexander Pashevich*, Igor Kalevatykh, Ivan Laptev, Josef Sivic, Cordelia Schmid
ICRA, 2020
bibtex / code / website / video

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

fast-texture Learning to Augment Synthetic Images for Sim2Real Policy Transfer
Alexander Pashevich*, Robin Strudel*, Igor Kalevatykh, Ivan Laptev, Cordelia Schmid
IROS, 2019
bibtex / code / website / video

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

fast-texture Modulated Policy Hierarchies
Alexander Pashevich, Danijar Hafner, James Davidson, Rahul Sukthankar, Cordelia Schmid
NeurIPS Deep RL Workshop, 2018
bibtex / poster

A hierarchical reinforcement learning approach for learning from sparse rewards.

fast-texture Plane-extraction from depth-data using a Gaussian mixture regression model
Richard Marriott, Alexander Pashevich, Radu Horaud
Pattern Recognition Letters, 2018
bibtex

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


website template credit