Najnowsze publikacje

• Marcin Sendera, Amin Sorkhei, Tomasz Kuśmierczyk, Revisiting the equivalence of Bayesian neural networks and Gaussian processes: on the importance of learning activations, Conference in Uncertainty in Artificial Intelligence [UAI] UAI '25: Proceedings of the Forty-First Conference on Uncertainty in Artificial Intelligence (2025), 3675 - 3700
• Marcin Sendera, Łukasz Struski, Kamil Książek, Kryspin Musiol, Jacek Tabor, Dawid Rymarczyk, SEMU: Singular Value Decomposition for Efficient Machine Unlearning, International Conference on Machine Learning [ICML] 267 Proceedings of Machine Learning (2025), 53843-53866
• Marcin Sendera, Amin Sorkhei, Tomasz Kuśmierczyk, Hi-fi functional priors by learning activations, Neurips Workshop On Bayesian Decision-making and Uncertainty 2024 (2024),
• Siddarth Venkatraman, Moksh Jain, Luca Scimeca, Minsu Kim, Marcin Sendera, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Bengio Emmanuel, Alexandre Adam, Jarrid Rector-Brooks, Yoshua Bengio, Glen Berseth, Nikolay Malkin, Amortizing intractable inference in diffusion models for vision, language, and control, Advances in Neural Information Processing Systems [NeurIPS] 37 (2024), 1-35
• Marcin Sendera, Minsu Kim, Sarthak Mittal, Pablo Lemos, Luca Scimeca, Jarrid Rector-Brooks, Alexandre Adam, Yoshua Bengio, Nikolay Malkin, Improved off-policy training of diffusion samplers, Advances in Neural Information Processing Systems [NeurIPS] 37 (2024), 81016-81045