| Oct 01, 2026 | π Gromov-Wasserstein Distillation for Inductive Multi-View Embedding, with Rafael Pereira Eufrazio and Charles Casimiro Cavalcante, accepted at the GDDL workshop at NeurIPS 2026. |
| Aug 01, 2026 | π Nonlinear Dimensionality Reduction through Optimal Transport between Incomparable Spaces, with Rafael Pereira Eufrazio and Charles Casimiro Cavalcante, is published in Information Geometry. |
| Jun 01, 2026 | π Wasserstein Gradient Flows for Scalable and Regularized Barycenter Computation accepted at UAI 2026. |
| Mar 27, 2026 | π Our paper ReBaPL: Repulsive Bayesian Prompt Learning was accepted at CVPR 2026. |
| Aug 01, 2025 | π Started a new role as AI Researcher at Sigma Nova, working on pre-training, fine-tuning, and transfer learning of large-scale foundation models for neuroscience and time series forecasting. |
| May 01, 2025 | π Optimal Transport for Domain Adaptation through Gaussian Mixture Models is now published in Transactions on Machine Learning Research (TMLR). |
| Apr 01, 2025 | π Unsupervised Anomaly Detection through Mass Repulsing Optimal Transport accepted at Transactions on Machine Learning Research (TMLR). |
| Mar 15, 2025 | π Two papers accepted at Geometric Science of Information (GSI) 2025: KDΒ²M: A Unifying Framework for Feature Knowledge Distillation and A Dimensionality Reduction Technique Based on the Gromov-Wasserstein Distance. |
| Sep 30, 2024 | π Defended my PhD thesis Multi-Source Domain Adaptation through Wasserstein Barycenters at UniversitΓ© Paris-Saclay (CEA-List). Director: Antoine Souloumiac. Advisor: Fred Maurice NgolΓ¨ Mboula. |
| Sep 09, 2024 | π Lighter, Better, Faster Multi-Source Domain Adaptation with Gaussian Mixture Models and Optimal Transport accepted at ECML-PKDD 2024. Code at github.com/eddardd/gmm_msda. |
| Apr 01, 2024 | π Our survey Recent Advances in Optimal Transport for Machine Learning is published in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). |
| Sep 30, 2023 | π Multi-Source Domain Adaptation through Dataset Dictionary Learning in Wasserstein Space (DaDiL) accepted at ECAI 2023. |