49 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- P. Piantanida7 · h 28
- Francisco Messina3 · h 7
- Malik Boudiaf3 · h 15
- Marco Romanelli3 · h 7
- Pablo Piantanida2 profiles3 · h 5
- F. Labeau2 · h 24
- Fr'ed'eric B'echet2 · h 2
- Georg Pichler2 profiles2 · h 9
- Ismail Ben Ayed2 profiles2 · h 52
- Marine Picot2 · h 4
- Pierre Colombo2 profiles2 · h 21
- Spyros Angelopoulos2 · h 15
- McGill UniversityCA6 papers
- Centre National de la Recherche ScientifiqueFR5 papers
- CentraleSupélecFR3 papers
- École de Technologie SupérieureCA3 papers
- Mila - Quebec Artificial Intelligence InstituteCA3 papers
- Institute for Learning and DevelopmentUS2 papers
- Laboratoire des signaux et systèmesFR2 papers
- Mathématiques et Informatique pour la Complexité et les Systèmes2 papers
- TU WienAT2 papers
- Universidad de Buenos AiresAR2 papers
- Université Paris-SaclayFR2 papers
- Aix-Marseille UniversitéFR1 paper
6 papers · 1 filter
Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog
Lautaro Estienne, Gabriel Ben Zenou, Nona Naderi +2
As AI systems take on collaborative roles, they must reason about shared goals and beliefs-not just generate fluent language. The Rational Speech Act (RSA) framework offers a princ…
LFAR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models
Santiago Cuervo, Adel Moumen, Yanis Labrak +5
Text-pretrained language models (LMs) encode rich world knowledge, but adapting them to process and generate perceptual modalities such as audio and images while effectively levera…
Part-Of-Speech Sensitivity of Routers in Mixture of Experts Models
Elie Antoine, Frédéric Béchet, Philippe Langlais
This study investigates the behavior of model-integrated routers in Mixture of Experts (MoE) models, focusing on how tokens are routed based on their linguistic features, specifica…
WikiFactDiff: A Large, Realistic, and Temporally Adaptable Dataset for Atomic Factual Knowledge Update in Causal Language Models
Hichem Ammar Khodja, Frédéric Béchet, Quentin Brabant +2
The factuality of large language model (LLMs) tends to decay over time since events posterior to their training are "unknown" to them. One way to keep models up-to-date could be fa…
Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models
Pierre Colombo, Victor Pellegrain, Malik Boudiaf +5
Proprietary and closed APIs are becoming increasingly common to process natural language, and are impacting the practical applications of natural language processing, including few…
Rainproof: An Umbrella To Shield Text Generators From Out-Of-Distribution Data
Maxime Darrin, Pablo Piantanida, Pierre Colombo
Implementing effective control mechanisms to ensure the proper functioning and security of deployed NLP models, from translation to chatbots, is essential. A key ingredient to ensu…