Publications

Non-Exchangeable Conformal Risk Control
António Farinhas, Chrysoula Zerva, Dennis Ulmer, André F. T. Martins. In Proceedings of ICLR, 2024 (to appear). [code]

An Empirical Study of Translation Hypothesis Ensembling with Large Language Models
António Farinhas, José G. C. Souza, André F. T. Martins. In Proceedings of EMNLP, 2023. [code]

Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation Patrick Fernandes, Aman Madaan, Emmy Liu, António Farinhas, Pedro H. Martins, Amanda Bertsch, José G. C. Souza, Shuyan Zhou, Tongshuang Wu, Graham Neubig, André F. T. Martins. In TACL, 2023.

Quality-Aware Decoding for Neural Machine Translation
Patrick Fernandes*, António Farinhas*, Ricardo Rei, José G. C. Souza, Perez Ogayo, Graham Neubig, André F. T. Martins. In Proceedings of NAACL, 2022. [code] [poster]

Sparse Communication via Mixed Distributions
António Farinhas, Wilker Aziz, Vlad Niculae, and André F. T. Martins. In Proceedings of ICLR, 2022. Oral presentation [code] [poster]

Sparse Continuous Distributions and Fenchel-Young Losses
André F. T. Martins, Marcos Treviso, António Farinhas, Pedro M. Q. Aguiar, Mário A. T. Figueiredo, Mathieu Blondel, and Vlad Niculae. In JMLR, 2022. [code]

Multimodal Continuous Visual Attention Mechanisms
António Farinhas, André F. T. Martins, and Pedro M. Q. Aguiar. In Proceedings of ICCV Workshops, 2021 [code] [poster]

Sparse and Continuous Attention Mechanisms
André F. T. Martins, António Farinhas, Marcos Treviso, Vlad Niculae, Pedro M. Q. Aguiar, and Mário A. T. Figueiredo. In Proceedings of NeurIPS, 2020. Spotlight presentation [code] [poster]