output
20202025
most citedTransductive Information Maximization For Few-Shot Learning

49 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions

17 papers

cs.CL2025

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…

cs.CL2025

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…

cs.DS2025

Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search

Ziyad Benomar, Lorenzo Croissant, Vianney Perchet +1

One-max search is a classic problem in online decision-making, in which a trader acts on a sequence of revealed prices and accepts one of them irrevocably to maximise its profit. T…

cs.LG2025

A Theoretical Justification for Asymmetric Actor-Critic Algorithms

Gaspard Lambrechts, Damien Ernst, Aditya Mahajan

In reinforcement learning for partially observable environments, many successful algorithms have been developed within the asymmetric learning paradigm. This paradigm leverages add…

cs.DS2025

Decision-Theoretic Approaches for Improved Learning-Augmented Algorithms

Spyros Angelopoulos, Christoph Dürr, Georgii Melidi

We initiate the systematic study of decision-theoretic metrics in the design and analysis of algorithms with machine-learned predictions. We introduce approaches based on both dete…

cs.CL2024

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…

cs.LG2024

Exposing the Vulnerability of Decentralized Learning to Membership Inference Attacks Through the Lens of Graph Mixing

Ousmane Touat, Jezekael Brunon, Yacine Belal +4

The primary promise of decentralized learning is to allow users to engage in the training of machine learning models in a collaborative manner while keeping their data on their pre…

cs.LG2024

Beyond the Norms: Detecting Prediction Errors in Regression Models

Andres Altieri, Marco Romanelli, Georg Pichler +2

This paper tackles the challenge of detecting unreliable behavior in regression algorithms, which may arise from intrinsic variability (e.g., aleatoric uncertainty) or modeling err…

cs.CL2024

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…

cs.CL2023

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…

stat.ML2023★ 2 cited

Fundamental Limits of Membership Inference Attacks on Machine Learning Models

Eric Aubinais, Elisabeth Gassiat, Pablo Piantanida

Membership inference attacks (MIA) can reveal whether a particular data point was part of the training dataset, potentially exposing sensitive information about individuals. This a…

cs.CL2022★ 2 cited

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…

cs.CV2022

MEAD: A Multi-Armed Approach for Evaluation of Adversarial Examples Detectors

Federica Granese, Marine Picot, Marco Romanelli +2

Detection of adversarial examples has been a hot topic in the last years due to its importance for safely deploying machine learning algorithms in critical applications. However, t…

cs.LG2022★ 15 cited

Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learning

Georg Pichler, Marco Romanelli, Leonardo Rey Vega +1

Federated Learning is expected to provide strong privacy guarantees, as only gradients or model parameters but no plain text training data is ever exchanged either between the clie…

cs.LG2021★ 27 cited

Adversarial Robustness via Fisher-Rao Regularization

Marine Picot, Francisco Messina, Malik Boudiaf +3

Adversarial robustness has become a topic of growing interest in machine learning since it was observed that neural networks tend to be brittle. We propose an information-geometric…

cs.LG2020★ 49 cited

Transductive Information Maximization For Few-Shot Learning

Malik Boudiaf, Ziko Imtiaz Masud, Jérôme Rony +3

We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions fo…

eess.SP2020★ 21 cited

Privacy-Cost Management in Smart Meters Using Deep Reinforcement Learning

Mohammadhadi Shateri, Francisco Messina, Pablo Piantanida +1

Smart meters (SMs) play a pivotal rule in the smart grid by being able to report the electricity usage of consumers to the utility provider (UP) almost in real-time. However, this…