AG
Alexandre Galashov
cs.LGcs.AIstat.MLcs.CLcs.CVcs.ROcs.GTcs.MAcs.NE
On Valency
published · living versionsW_5ke7j8fd·v1 · currentpublished
Sampling Interventional Distributions with Orthogonal MMD Flow
with Bariscan Bozkurt, Hugh Dance, Zonghao Chen, Arthur Gretton +1
1 version
Preprints & journals
30 papers in the corpus · 2018–2026Improved Distributional Diffusion Models2609.37147v1 · Tommaso Martorella, Alexandre Galashov, Felix Krause et al.2026 · 0 citationsarXiv
Simplex Diffusion Models2609.35553v1 · Justin Deschenaux, Alexandre Galashov, Andrew Campbell et al.2026 · 0 citationsarXiv
Adversarial Learning of Classifier-Free Guidance Schedules2608.14038v1 · Ashwini Pokle, Alexandre Galashov, Arnaud Doucet et al.2026 · 0 citationsarXiv
DiffusionGemma Technical Report2608.00146v1 · DiffusionGemma Team: Adrien Ali Taiga, James Assiene, Daniele Calandriello et al.2026 · 0 citationsarXiv
Doubly Robust Proxy Causal Learning with Neural Mean Embeddings2605.09514v2 · Bariscan Bozkurt, Alexandre Galashov, Dimitri Meunier et al.2026 · 0 citationsarXiv
On the Wasserstein Gradient Flow Interpretation of Drifting Models2605.05118v2 · Arthur Gretton, Li Kevin Wenliang, Alexandre Galashov et al.2026 · 0 citationsarXiv
Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production2510.13879v2 · Alexandre Galashov, Matt Jones, Rosemary Ke et al.2025 · 0 citationsarXiv
Closed-Form Last Layer Optimization2510.04606v2 · Alexandre Galashov, Nathael Da Costa, Liyuan Xu et al.2025 · 0 citationsarXiv
Learn to Guide Your Diffusion Model2510.00815v1 · Alexandre Galashov, Ashwini Pokle, Arnaud Doucet et al.2025 · 0 citationsarXiv
Distributional Diffusion Models with Scoring Rules2502.02483v3 · Valentin De Bortoli, Alexandre Galashov, J. Swaroop Guntupalli et al.2025 · 1 citationarXiv
Accelerated Diffusion Models via Speculative Sampling2501.05370v2 · Valentin De Bortoli, Alexandre Galashov, Arthur Gretton et al.2025 · 0 citationsarXiv
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset2411.04034v1 · Alexandre Galashov, Michalis K. Titsias, Andr'as Gyorgy et al.2024 · 1 citationNeurIPS 2024
Deep MMD Gradient Flow without adversarial training2405.06780v1 · Alexandre Galashov, Valentin de Bortoli, Arthur Gretton2024 · 0 citationsarXiv
Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models2403.01518v1 · Amal Rannen-Triki, Jorg Bornschein, Razvan Pascanu et al.2024 · 1 citationarXiv
Kalman Filter for Online Classification of Non-Stationary Data2306.08448v1 · Michalis K. Titsias, Alexandre Galashov, Amal Rannen-Triki et al.2023 · 1 citationICLR 2024
Towards Compute-Optimal Transfer Learning2304.13164v1 · Massimo Caccia, Alexandre Galashov, Arthur Douillard et al.2023 · 2 citationsarXiv
NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research2211.11747v2 · Jorg Bornschein, Alexandre Galashov, Ross Hemsley et al.2022 · 3 citationsarXiv
Data augmentation for efficient learning from parametric experts2205.11448v1 · Alexandre Galashov, Josh Merel, Nicolas Heess2022 · 3 citationsarXiv
Game Plan: What AI can do for Football, and What Football can do for AI2011.09192v1 · Karl Tuyls, Shayegan Omidshafiei, Paul Muller et al.2020 · 116 citationsarXiv
Behavior Priors for Efficient Reinforcement Learning2010.14274v1 · Dhruva Tirumala, Alexandre Galashov, Hyeonwoo Noh et al.2020 · 18 citationsarXiv
Learning Dexterous Manipulation from Suboptimal Experts2010.08587v2 · Rae Jeong, Jost Tobias Springenberg, Jackie Kay et al.2020 · 15 citationsarXiv
Temporal Difference Uncertainties as a Signal for Exploration2010.02255v2 · Sebastian Flennerhag, Jane X. Wang, Pablo Sprechmann et al.2020 · 7 citationsarXiv
Importance Weighted Policy Learning and Adaptation2009.04875v2 · Alexandre Galashov, Jakub Sygnowski, Guillaume Desjardins et al.2020 · 1 citationarXiv
Information Theoretic Meta Learning with Gaussian Processes2009.03228v3 · Michalis K. Titsias, Francisco J. R. Ruiz, Sotirios Nikoloutsopoulos et al.2020 · 6 citationsarXiv
Task Agnostic Continual Learning via Meta Learning1906.05201v1 · Xu He, Jakub Sygnowski, Alexandre Galashov et al.2019 · 59 citationsarXiv
Meta reinforcement learning as task inference1905.06424v2 · Jan Humplik, Alexandre Galashov, Leonard Hasenclever et al.2019 · 62 citationsarXiv
Information asymmetry in KL-regularized RL1905.01240v1 · Alexandre Galashov, Siddhant M. Jayakumar, Leonard Hasenclever et al.2019 · 41 citationsarXiv
Meta-Learning surrogate models for sequential decision making1903.11907v2 · Alexandre Galashov, Jonathan Schwarz, Hyunjik Kim et al.2019 · 9 citationsarXiv
Exploiting Hierarchy for Learning and Transfer in KL-regularized RL1903.07438v2 · Dhruva Tirumala, Hyeonwoo Noh, Alexandre Galashov et al.2019 · 22 citationsarXiv
Neural probabilistic motor primitives for humanoid control1811.11711v2 · Josh Merel, Leonard Hasenclever, Alexandre Galashov et al.2018 · 93 citationsarXiv
Career total: 33 works. 30 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.