Alexandre Galashov

MS student, Ecole Polytechnique

Joined

February 2018

Names

Alexandre Galashov

Emails

****@google.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Homepage

Career & Education History

MS student

Ecole Polytechnique (polytechnique.edu)

2013 – 2026

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

Learn to Guide Your Diffusion Model
Alexandre Galashov, Ashwini Pokle, Arnaud Doucet, Arthur Gretton, Mauricio Delbracio, Valentin De Bortoli
- ICLR 2026 Poster
- Readers: Everyone
Closed-form Last Layer Optimization
Alexandre Galashov, Nathaël Da Costa, Liyuan Xu, Philipp Hennig, Arthur Gretton
- Submitted to ICLR 2026
- Readers: Everyone
Accelerated Diffusion Models via Speculative Sampling
Valentin De Bortoli, Alexandre Galashov, Arthur Gretton, Arnaud Doucet
- ICML 2025 poster
- Readers: Everyone
Distributional Diffusion Models with Scoring Rules
Valentin De Bortoli, Alexandre Galashov, J Swaroop Guntupalli, Guangyao Zhou, Kevin Patrick Murphy, Arthur Gretton, Arnaud Doucet
- ICML 2025 poster
- Readers: Everyone
Deep MMD Gradient Flow without adversarial training
Alexandre Galashov, Valentin De Bortoli, Arthur Gretton
- ICLR 2025 Poster
- Readers: Everyone
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset
Alexandre Galashov, Michalis Titsias, András György, Clare Lyle, Razvan Pascanu, Yee Whye Teh, Maneesh Sahani
- NeurIPS 2024 poster
- Readers: Everyone
Stochastic linear dynamics in parameters to deal with Neural Networks plasticity loss
Alexandre Galashov, Michalis Titsias, Razvan Pascanu, Yee Whye Teh, Maneesh Sahani
- DistShift 2023 Poster
- Readers: Everyone
Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models
Amal Rannen-Triki, Jorg Bornschein, Razvan Pascanu, Alexandre Galashov, Michalis Titsias, Marcus Hutter, András György, Yee Whye Teh
- DistShift 2023 Poster
- Readers: Everyone
Kalman Filter for Online Classification of Non-Stationary Data
Michalis Titsias, Alexandre Galashov, Amal Rannen-Triki, Razvan Pascanu, Yee Whye Teh, Jorg Bornschein
- ICLR 2024 poster
- Readers: Everyone
Data augmentation for efficient learning from parametric experts
Alexandre Galashov, Josh Merel, Nicolas Heess
- Published: 31 Oct 2022, Last Modified: 11 Oct 2022
- NeurIPS 2022 Accept
- Readers: Everyone

View all 15 publications

Co-Authors

View all 40 co-authors