dr 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] vol. UAI '25: Proceedings of the Forty-First Conference on Uncertainty in Artificial Intelligence (2025), 3675 - 3700

Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA, Empirical Methods in Natural Language Processing [EMNLP](MAIN), (2025),

ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data, Advances in Neural Information Processing Systems [NeurIPS](MAIN), (2025),

Hypernetwork Approach to Bayesian MAML (Student Abstract), National Conference of the American Association for Artificial Intelligence [AAAI] vol. 39 (2025), 29325-29327

Hi-fi functional priors by learning activations, Neurips Workshop On Bayesian Decision-making and Uncertainty 2024 (2024),