head.png

Nathanaël Carraz Rakotonirina


Hello there 👋! I am a PhD student at Universitat Pompeu Fabra, supervised by Marco Baroni. I am interested in Robustness, Controllability and Interpretability of Large Language Models. I am currently working on the ALiEN project.

Selected publications

2024

  1. arch_memoryprompt.png
    MemoryPrompt: A Light Wrapper to Improve Context Tracking in Pre-trained Language Models
    Nathanaël Carraz Rakotonirina, and Marco Baroni
    LREC-COLING, 2024

2023

  1. Optimizing with low budgets: A comparison on the black-box optimization benchmarking suite and openai gym
    Elena Raponi, Nathanaël Carraz Rakotonirina, Jérémy Rapin, Carola Doerr, and Olivier Teytaud
    IEEE Transactions on Evolutionary Computation, 2023
  2. universal_prompt.png
    Can discrete information extraction prompts generalize across language models?
    Nathanaël Carraz Rakotonirina, Roberto Dessı̀, Fabio Petroni, Sebastian Riedel, and Marco Baroni
    ICLR, 2023
  3. eme_cap.png
    Cross-Domain Image Captioning with Discriminative Finetuning
    Roberto Dessı̀, Michele Bevilacqua, Eleonora Gualdoni, Nathanaël Carraz Rakotonirina, Francesca Franzon, and Marco Baroni
    CVPR, 2023
  4. speech_emb.png
    Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili
    Christiaan Jacobs, Nathanaël Carraz Rakotonirina, Everlyn Asiko Chimoto, Bruce A Bassett, and Herman Kamper
    INTERSPEECH, 2023

2022

  1. Fairness in generative modeling: do it unsupervised!
    Mariia Zameshina, Olivier Teytaud, Fabien Teytaud, Vlad Hosu, Nathanaël Carraz Rakotonirina, Laurent Najman, and Markus Wagner
    GECCO, 2022

2021

  1. many_objective.png
    Many-Objective Optimization for Diverse Image Generation
    Nathanaël Carraz Rakotonirina, Andry Rasoanaivo, Laurent Najman, Petr Kungurtsev, Jeremy Rapin, Fabien Teytaud, Baptiste Roziere, Olivier Teytaud, Markus Wagner, Pak-Kan Wong, and  others
    ArXiv preprint, 2021
  2. audio_super.png
    Self-attention for audio super-resolution
    Nathanaël Carraz Rakotonirina
    MLSP, 2021
  3. tarsier.png
    Tarsier: Evolving noise injection in super-resolution gans
    Baptiste Roziere, Nathanaël Carraz Rakotonirina, Vlad Hosu, Andry Rasoanaivo, Hanhe Lin, Camille Couprie, and Olivier Teytaud
    ICPR, 2021

2020

  1. esrganplus.png
    ESRGAN+: Further improving enhanced super-resolution generative adversarial network
    Nathanaël Carraz Rakotonirina, and Andry Rasoanaivo
    ICASSP, 2020

Teaching

Introduction to Machine Learning
Université d’Antananarivo, MISA

NVIDIA DLI University Ambassador