Frédéric Armetta
YOU?
Author Swipe
Large Language Models and Algorithm Execution: Application to an Arithmetic Function Open
Large Language Models (LLMs) have recently developed new advanced functionalities. Their effectiveness relies on statistical learning and generalization capabilities. However, they face limitations in internalizing the data they process an…
View article: Leveraging Graph Structures and Large Language Models for End-to-End Synthetic Task-Oriented Dialogues
Leveraging Graph Structures and Large Language Models for End-to-End Synthetic Task-Oriented Dialogues Open
Training task-oriented dialogue systems is both costly and time-consuming, due to the need for high-quality datasets encompassing diverse intents. Traditional methods depend on extensive human annotation, while recent advancements leverage…
Autonomie et représentation de l'environnement Open
One of the major challenges of AI is the design of a suitable representation to organize knowledge and exploit it. In the context of the work presented, I focus on the autonomous design of this representation, by an embodied agent that exp…
View article: Assisted Debate Builder with Large Language Models
Assisted Debate Builder with Large Language Models Open
We introduce ADBL2, an assisted debate builder tool. It is based on the capability of large language models to generalise and perform relation-based argument mining in a wide-variety of domains. It is the first open-source tool that levera…
Unraveling the thread: understanding and addressing sequential failures in human-robot interaction Open
Interaction is a dynamic process that evolves in real time. Participants interpret and orient themselves towards turns of speech based on expectations of relevance and social/conversational norms (that have been extensively studied in the …
View article: Assisted Debate Builder with Large Language Models
Assisted Debate Builder with Large Language Models Open
We introduce ADBL2, an assisted debate builder tool. It is based on the capability of large language models to generalise and perform relation-based argument mining in a wide-variety of domains. It is the first open-source tool that levera…
Algorithmic learning, a next step for AI. An application to arithmetic operations Open
International audience
Sequential annotations for naturally-occurring HRI: first insights Open
We explain the methodology we developed for improving the interactions accomplished by an embedded conversational agent, drawing from Conversation Analytic sequential and multimodal analysis. The use case is a Pepper robot that is expected…
The Impact of Action in Visual Representation Learning Open
International audience
Novelty detection for unsupervised continual learning in image sequences Open
International audience
Learning Arithmetic Operations With A Multistep Deep Learning Open
International audience
Determining Citation Blocks using End-to-end Neural Coreference Resolution Model for Citation Context Analysis Open
International audience
Identifying the Conceptual Space of Citation Contexts using Coreferences. Open
International audience
A preliminary study to compare deep learning with rule-based approaches for citation classification Open
International audience
Autonomous object recognition in videos using Siamese Neural Networks Open
International audience
Extracting tags from large raw texts using End-to-End memory networks Open
International audience
A Self-Acquiring Knowledge Process for MCTS Open
MCTS (Monte Carlo Tree Search) is a well-known and efficient process to cover and evaluate a large range of states for combinatorial problems. We choose to study MCTS for the Computer Go problem, which is one of the most challenging proble…