![](/assets/images/profile_photo.jpg)
Hi! I'm Alexandra
I'm doing PhD in computer science at Université de Montréal and Mila with Prof. Yoshua Bengio. My research is focused on applications of generative models for drug discovery and material design.
As a computer scientist, I'm concerned about existing and potential harms which technologies are bringing to this world. In my PhD journey, I'm exploring the ways of advancing socially-beneficial applications of machine learning and acting against its misuses.
In the Mila community, I'm a member of Sustainability Committee and a co-organizer of Against Military AI reading group. In 2022/2023, I was elected as a student Lab Representative.
Publications
-
Towards equilibrium molecular conformation generation with GFlowNets
Alexandra Volokhova*, Michał Koziarski*, Alex Hernández-García, Cheng-Hao Liu, Santiago Miret, Pablo Lemos, Luca Thiede, Zichao Yan, Alán Aspuru-Guzik, Yoshua Bengio
Digital Discovery
code -
Crystal-GFN: sampling crystals with desirable properties and constraints
Mila AI4Science, Alex Hernandez-Garcia, Alexandre Duval, Alexandra Volokhova, Yoshua Bengio, Divya Sharma, Pierre Luc Carrier, Yasmine Benabed, Michał Koziarski, Victor Schmidt
AI4Mat workshop @ Neurips 2023
code -
A theory of continuous generative flow networks
Salem Lahlou, Tristan Deleu, Pablo Lemos, Dinghuai Zhang, Alexandra Volokhova, Alex Hernández-García, Léna Néhale Ezzine, Yoshua Bengio, Nikolay Malkin
ICML 2023 -
Generative Flow Networks for Discrete Probabilistic Modeling
Dinghuai Zhang, Nikolay Malkin, Zhen Liu, Alexandra Volokhova, Aaron Courville, Yoshua Bengio
ICML 2022 -
Stochasticity in Neural ODEs: An Empirical Study
Viktor Oganesyan*, Alexandra Volokhova*, Dmitry Vetrov
Integration of Deep Neural Models and Differential Equations workshop @ ICLR 2020
code -
Cherenkov detectors fast simulation using neural networks
Denis Derkach, Nikita Kazeev, Fedor Ratnikov, Andrey Ustyuzhanin, Alexandra Volokhova
Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment -
Semi-Conditional Normalizing Flows for Semi-Supervised Learning
Andrew Atanov, Alexandra Volokhova, Arsenii Ashukha, Ivan Sosnovik, Dmitry Vetrov
Invertible Neural Nets and Normalizing Flows workshop @ ICML 2019
code
Events
- Harms and Risks of AI in the Military Workshop, Mila, Dec 2024, leading co-organizer
- GFlowNet Workshop, Mila, Nov 2023, co-organizer
- AI Helps Ukraine Charity Conference, Mila, Nov-Dec 2022, leading co-organizer
- New In ML workshop, NeurIPS, Dec 2022, co-organizer
Teaching
- Université de Montréal: Representation learning, winter 2023, teaching assistant
- AI4Good Lab: Summer school in AI, summer 2022, teaching assistant
- YSDA: Bayesian methods in Machine Learning, fall 2020, practical sessions instructor
- HSE: Machine Learning 1, fall 2019, practical sessions instructor
- YSDA: Bayesian methods in Machine Learning, fall 2019, practical sessions instructor
- HSE: Introduction to programming, fall 2018, practical sessions instructor
- MIPT Olympiad summer school, summer 2016, teaching assistant
Activities
![](/assets/images/fire.jpg)
At night, I'm a multidisciplinary artist. My current passion is flow art and cirques. I dance with fire, juggle, do aerial and hand-to-hand acrobatics.
Recently, I became an aerial yoga teacher and started giving classes in Montreal.
During my hight school, I graduated from the International School of Floral Design ”Nikole” as a master of design and floristics. Although I've never worked as a designer, I like drawing and crafting from time to time. You can find some of my art on Instagram.
I deeply love our planet and all its inhabitants, that's why I'm vegan and I like spending my vacations hiking in nature with my family and friends.