Nathanaël Carraz Rakotonirina — accepted AI-conference papers

2025

From Tools to Teammates: Evaluating LLMs in Multi-Session Coding Interactions

Nathanaël Carraz Rakotonirina, Mohammed Hamdy, Jon Ander Campos, Lucas Weber, Alberto Testoni, Marzieh Fadaee +2

ACL 2025long

Large Language Models (LLMs) are increasingly used in working environments for a wide range of tasks, excelling at solving individual problems in isolation. However, are they also able to effectively collaborate over long-term interactions? To investigate this, we introduce MemoryCode, a synthetic m…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

Can discrete information extraction prompts generalize across language models?

Nathanaël Carraz Rakotonirina, Roberto Dessi, Fabio Petroni, Sebastian Riedel, Marco Baroni

ICLR 2023poster

We study whether automatically-induced prompts that effectively extract information from a language model can also be used, out-of-the-box, to probe other language models for the same information. After confirming that discrete prompts induced with the AutoPrompt algorithm outperform manual and semi…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗

2023

Cross-Domain Image Captioning With Discriminative Finetuning

Roberto Dessì, Michele Bevilacqua, Eleonora Gualdoni, Nathanaël Carraz Rakotonirina, Francesca Franzon, Marco Baroni

CVPR 2023poster

Neural captioners are typically trained to mimic human-generated references without optimizing for any specific communication goal, leading to problems such as the generation of vague captions. In this paper, we show that fine-tuning an out-of-the-box neural captioner with a self-supervised discrimi…

Cited by 22 Source ↗PDF ↗code ↗Scholar ↗

2020

ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network

Nathanaël Carraz Rakotonirina, Andry Rasoanaivo

ICASSP 2020accepted

Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) is a perceptual-driven approach for single image super-resolution that is able to produce photorealistic images. Despite the visual quality of these generated images, there is still room for improvement. In this fashion, the model is…

Cited by 0 Source ↗Scholar ↗