Ujváry, Szilvia

6 publications

ICLRW 2025 Implicit Bayesian Inference Is an Insufficient Explanation of Language Model Behaviour in Compositional Tasks Szilvia Ujváry, Anna Mészáros, Wieland Brendel, Patrik Reizinger, Ferenc Huszár

ICML 2024 Position: Understanding LLMs Requires More than Statistical Generalization Patrik Reizinger, Szilvia Ujváry, Anna Mészáros, Anna Kerekes, Wieland Brendel, Ferenc Huszár

NeurIPS 2024 Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts Anna Mészáros, Szilvia Ujváry, Wieland Brendel, Patrik Reizinger, Ferenc Huszár

NeurIPSW 2024 Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts Anna Mészáros, Szilvia Ujváry, Wieland Brendel, Patrik Reizinger, Ferenc Huszár

NeurIPSW 2023 Estimating Optimal PAC-Bayes Bounds with Hamiltonian Monte Carlo Szilvia Ujváry, Gergely Flamich, Vincent Fortuin, José Miguel Hernández-Lobato

NeurIPSW 2022 Rethinking Sharpness-Aware Minimization as Variational Inference Szilvia Ujváry, Zsigmond Telek, Anna Kerekes, Anna Mészáros, Ferenc Huszár