Aziz, Wilker

6 publications

ICLR 2026 Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations Pedro Lobato Ferreira, Wilker Aziz, Ivan Titov

CVPRW 2023 Vision DiffMask: Faithful Interpretation of Vision Transformers with Differentiable Patch Masking Angelos Nalmpantis, Apostolos Panagiotopoulos, John Gkountouras, Konstantinos Papakostas, Wilker Aziz

ICLR 2022 Sparse Communication via Mixed Distributions António Farinhas, Wilker Aziz, Vlad Niculae, Andre Martins

ICLR 2020 A Latent Morphology Model for Open-Vocabulary Neural Machine Translation Duygu Ataman, Wilker Aziz, Alexandra Birch

NeurIPS 2020 Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity Gonçalo Correia, Vlad Niculae, Wilker Aziz, André Martins

UAI 2019 Block Neural Autoregressive Flow Nicola De Cao, Wilker Aziz, Ivan Titov