Kolya Malkin is a postdoctoral fellow at Mila – Québec AI Institute and Université de Montréal in Montréal, Québec, Canada and a member of Prof. Yoshua Bengio's research group. He was formally trained as a pure mathematician: at the University of Washington (Seattle) (B.S., 2015) and Yale University (M.S. and Ph.D., 2021).

He mainly works on deep-learning-based reasoning and its applications, in particular:

Generative models, in particular, induction of compositional structure in generative models and modeling of posteriors over high-dimensional explanatory variables. Much of my recent work is on generative flow networks, or GFlowNets, which are a path towards inference machines that build structured, uncertainty-aware explanations for observed data.

Applications to natural language processing: what large language models can do, what they cannot do, and how to overcome their limitations with inference procedures that induce behaviours more akin to human reasoning.

Applications to computer vision: notably, below you can find my work on AI for remote sensing (land cover mapping and change detection), which can be used for tracking land use patterns over time and monitoring the effects of climate change.