AIConfPaper
← Search

Patrick Gallinari

32 accepted papers

2025

Context Copying Modulation: The Role of Entropy Neurons in Managing Parametric and Contextual Knowledge Conflicts

Zineddine Tighidet, Andrea Mogini, Hedi Ben younes, Jiali Mei, Patrick Gallinari, Benjamin Piwowarski
EMNLP 2025

The behavior of Large Language Models (LLMs) when facing contextual information that conflicts with their internal parametric knowledge is inconsistent, with no generally accepted explanation for the expected outcome distribution. Recent work has identified in autoregressive transformer models a cla

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

ENMA: Tokenwise Autoregression for Continuous Neural PDE Operators

Armand Kassaï Koupaï, Lise Le Boudec, Louis Serrano, Patrick Gallinari
NeurIPS 2025spotlight

Solving time-dependent parametric partial differential equations (PDEs) remains a fundamental challenge for neural solvers, particularly when generalizing across a wide range of physical parameters and dynamics. When data is uncertain or incomplete—as is often the case—a natural approach is to turn…

Cited by 0Source ↗Scholar ↗
2025

Learning a Neural Solver for Parametric PDEs to Enhance Physics-Informed Methods

Lise Le Boudec, Emmanuel de Bezenac, Louis Serrano, Ramon Daniel Regueiro-Espino, Yuan Yin, Patrick Gallinari
ICLR 2025poster

Physics-informed deep learning often faces optimization challenges due to the complexity of solving partial differential equations (PDEs), which involve exploring large solution spaces, require numerous iterations, and can lead to unstable training. These challenges arise particularly from the ill-c…

Cited by 2Source ↗PDF ↗Scholar ↗
2025

MEXMA: Token-level objectives improve sentence representations

João Maria Janeiro, Benjamin Piwowarski, Patrick Gallinari, Loic Barrault
ACL 2025long

Cross-lingual sentence encoders (CLSE) create fixed-size sentence representations with aligned translations. Current pre-trained CLSE approaches use sentence-level objectives only. This can lead to loss of information, especially for tokens, which then degrades the sentence representation. We propos…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Mixture of Languages: Improved Multilingual Encoders Through Language Grouping

Jo{\~a}o Maria Janeiro, Belen Alastruey, Francisco Massa, Maha Elbayad, Benjamin Piwowarski, Patrick Gallinari +1
EMNLP 2025

We propose Mixture of Languages (MoL), a new strategy to pretrain largely multilingual encoders. Recent work in this field has relied on training transformer encoders on a large amount of multilingual data, with all parameters shared across all languages, without studying how to optimally balance la

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation

Song Duong, Florian Le Bronnec, Alexandre Allauzen, Vincent Guigue, Alberto Lumbreras, Laure Soulier +1
ICLR 2025poster

Large Language Models (LLMs), when used for conditional text generation, often produce hallucinations, i.e., information that is unfaithful or not grounded in the input context. This issue arises in typical conditional text generation tasks, such as text summarization and data-to-text generation, wh…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Zebra: In-Context Generative Pretraining for Solving Parametric PDEs

Louis Serrano, Armand Kassaï Koupaï, Thomas X Wang, Pierre ERBACHER, Patrick Gallinari
ICML 2025poster

Solving time-dependent parametric partial differential equations (PDEs) is challenging for data-driven methods, as these models must adapt to variations in parameters such as coefficients, forcing terms, and initial conditions. State-of-the-art neural surrogates perform adaptation through gradient-b…

Cited by 2Source ↗PDF ↗Scholar ↗
2024

AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields

Louis Serrano, Thomas X Wang, Etienne Le Naour, Jean-Noël Vittaut, Patrick Gallinari
NeurIPS 2024poster

We present AROMA (Attentive Reduced Order Model with Attention), a framework designed to enhance the modeling of partial differential equations (PDEs) using local neural fields. Our flexible encoder-decoder architecture can obtain smooth latent representations of spatial physical fields from a varie…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2024

Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning

Armand Kassaï Koupaï, Jorge Mifsut Benet, Yuan Yin, Jean-Noël Vittaut, Patrick Gallinari
NeurIPS 2024poster

Solving parametric partial differential equations (PDEs) presents significant challenges for data-driven methods due to the sensitivity of spatio-temporal dynamics to variations in PDE parameters. Machine learning approaches often struggle to capture this variability. To address this, data-driven ap…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2023

Continuous PDE Dynamics Forecasting with Implicit Neural Representations

Yuan Yin, Matthieu Kirchmeyer, Jean-Yves Franceschi, Alain Rakotomamonjy, patrick gallinari
ICLR 2023top-25%

Effective data-driven PDE forecasting methods often rely on fixed spatial and / or temporal discretizations. This raises limitations in real-world applications like weather prediction where flexible extrapolation at arbitrary spatiotemporal locations is required. We address this problem by introduci…

Cited by 82Source ↗PDF ↗code ↗Scholar ↗
2023

Learning from Multiple Sources for Data-to-Text and Text-to-Data

Song Duong, Alberto Lumbreras, Mike Gartrell, Patrick Gallinari
AISTATS 2023poster

Data-to-text (D2T) and text-to-data (T2D) are dual tasks that convert structured data, such as graphs or tables into fluent text, and vice versa. These tasks are usually handled separately and use corpora extracted from a single source. Current systems leverage pre-trained language models fine-tuned…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2023

Module-wise Training of Neural Networks via the Minimizing Movement Scheme

Skander Karkar, Ibrahim Ayed, Emmanuel de Bezenac, patrick gallinari
NeurIPS 2023poster

Greedy layer-wise or module-wise training of neural networks is compelling in constrained and on-device settings where memory is limited, as it circumvents a number of problems of end-to-end back-propagation. However, it suffers from a stagnation problem, whereby early layers overfit and deeper laye…

Cited by 3Source ↗PDF ↗Scholar ↗
2023

Operator Learning with Neural Fields: Tackling PDEs on General Geometries

Louis Serrano, Lise Le Boudec, Armand Kassaï Koupaï, Thomas X Wang, Yuan Yin, Jean-Noël Vittaut +1
NeurIPS 2023poster

Machine learning approaches for solving partial differential equations require learning mappings between function spaces. While convolutional or graph neural networks are constrained to discretized functions, neural operators present a promising milestone toward mapping functions directly. Despite i…

Cited by 42Source ↗PDF ↗code ↗Scholar ↗
2022

A Neural Tangent Kernel Perspective of GANs

Jean-Yves Franceschi, Emmanuel De Bézenac, Ibrahim Ayed, Mickael Chen, Sylvain Lamprier, Patrick Gallinari
ICML 2022spotlight

We propose a novel theoretical framework of analysis for Generative Adversarial Networks (GANs). We reveal a fundamental flaw of previous analyses which, by incorrectly modeling GANs’ training scheme, are subject to ill-defined discriminator gradients. We overcome this issue which impedes a principl…

Cited by 26Source ↗PDF ↗code ↗Scholar ↗
2022

AirfRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged Navier–Stokes Solutions

Florent Bonnet, Jocelyn Ahmed Mazari, Paola Cinnella, patrick gallinari
NeurIPS 2022accept

Surrogate models are necessary to optimize meaningful quantities in physical dynamics as their recursive numerical resolutions are often prohibitively expensive. It is mainly the case for fluid dynamics and the resolution of Navier–Stokes equations. However, despite the fast-growing field of data-dr…

Cited by 72Source ↗PDF ↗Scholar ↗
2022

Constrained Physical-Statistics Models for Dynamical System Identification and Prediction

Jérémie DONA, Marie Déchelle, patrick gallinari, Marina Levy
ICLR 2022poster

Modeling dynamical systems combining prior physical knowledge and machine learning (ML) is promising in scientific problems when the underlying processes are not fully understood, e.g. when the dynamics is partially known. A common practice to identify the respective parameters of the physical and M…

Cited by 11Source ↗PDF ↗Scholar ↗
2022

Diverse Weight Averaging for Out-of-Distribution Generalization

Alexandre Rame, Matthieu Kirchmeyer, Thibaud Rahier, Alain Rakotomamonjy, patrick gallinari, Matthieu Cord
NeurIPS 2022accept

Standard neural networks struggle to generalize under distribution shifts in computer vision. Fortunately, combining multiple networks can consistently improve out-of-distribution generalization. In particular, weight averaging (WA) strategies were shown to perform best on the competitive DomainBed…

Cited by 147Source ↗PDF ↗code ↗Scholar ↗
2022

Generalizing to New Physical Systems via Context-Informed Dynamics Model

Matthieu Kirchmeyer, Yuan Yin, Jeremie Dona, Nicolas Baskiotis, Alain Rakotomamonjy, Patrick Gallinari
ICML 2022spotlight

Data-driven approaches to modeling physical systems fail to generalize to unseen systems that share the same general dynamics with the learning domain, but correspond to different physical contexts. We propose a new framework for this key problem, context-informed dynamics adaptation (CoDA), which t…

Cited by 47Source ↗PDF ↗code ↗Scholar ↗
2022

Mapping conditional distributions for domain adaptation under generalized target shift

Matthieu Kirchmeyer, Alain Rakotomamonjy, Emmanuel de Bezenac, patrick gallinari
ICLR 2022poster

We consider the problem of unsupervised domain adaptation (UDA) between a source and a target domain under conditional and label shift a.k.a Generalized Target Shift (GeTarS). Unlike simpler UDA settings, few works have addressed this challenging problem. Recent approaches learn domain-invariant rep…

Cited by 28Source ↗PDF ↗code ↗Scholar ↗
2021

Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting

Yuan Yin, Vincent LE GUEN, Jérémie DONA, Emmanuel de Bezenac, Ibrahim Ayed, Nicolas THOME +1
ICLR 2021oral

Forecasting complex dynamical phenomena in settings where only partial knowledge of their dynamics is available is a prevalent problem across various scientific fields. While purely data-driven approaches are arguably insufficient in this context, standard physical modeling based approaches tend to…

Cited by 199Source ↗PDF ↗code ↗Scholar ↗
2021

Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation

Clement Rebuffel, Thomas Scialom, Laure Soulier, Benjamin Piwowarski, Sylvain Lamprier, Jacopo Staiano +2
EMNLP 2021main

QuestEval is a reference-less metric used in text-to-text tasks, that compares the generated summaries directly to the source text, by automatically asking and answering questions. Its adaptation to Data-to-Text tasks is not straightforward, as it requires multimodal Question Generation and Answerin…

Cited by 30Source ↗PDF ↗code ↗Scholar ↗
2021

LEADS: Learning Dynamical Systems that Generalize Across Environments

Yuan Yin, Ibrahim Ayed, Emmanuel de Bezenac, Nicolas Baskiotis, patrick gallinari
NeurIPS 2021poster

When modeling dynamical systems from real-world data samples, the distribution of data often changes according to the environment in which they are captured, and the dynamics of the system itself vary from one environment to another. Generalizing across environments thus challenges the conventional…

Cited by 45Source ↗PDF ↗code ↗Scholar ↗
2021

PDE-Driven Spatiotemporal Disentanglement

Jérémie Donà, Jean-Yves Franceschi, sylvain lamprier, patrick gallinari
ICLR 2021poster

A recent line of work in the machine learning community addresses the problem of predicting high-dimensional spatiotemporal phenomena by leveraging specific tools from the differential equations theory. Following this direction, we propose in this article a novel and general paradigm for this task b…

Cited by 43Source ↗PDF ↗code ↗Scholar ↗
2021

QuestEval: Summarization Asks for Fact-based Evaluation

Thomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano, Alex Wang +1
EMNLP 2021main

Summarization evaluation remains an open research problem: current metrics such as ROUGE are known to be limited and to correlate poorly with human judgments. To alleviate this issue, recent work has proposed evaluation metrics which rely on question answering models to assess whether a summary cont…

Cited by 281Source ↗PDF ↗code ↗Scholar ↗
2021

Separating Retention from Extraction in the Evaluation of End-to-end Relation Extraction

Bruno Taillé, Vincent Guigue, Geoffrey Scoutheeten, Patrick Gallinari
EMNLP 2021main

State-of-the-art NLP models can adopt shallow heuristics that limit their generalization capability (McCoy et al., 2019). Such heuristics include lexical overlap with the training set in Named-Entity Recognition (Taille et al., 2020) and Event or Type heuristics in Relation Extraction (Rosenman et a…

Cited by 7Source ↗PDF ↗code ↗Scholar ↗
2020

Deep-SST-Eddies: A Deep Learning Framework to Detect Oceanic Eddies in Sea Surface Temperature Images

Evangelos Moschos, Olivier Schwander, Alexandre Stegner, Patrick Gallinari
ICASSP 2020accepted

Until now, mesoscale oceanic eddies have been automatically detected through physical methods on satellite altimetry. Nevertheless, they often have a visible signature on Sea Surface Temperature (SST) satellite images, which have not been yet sufficiently exploited. We introduce a novel method that…

Cited by 0Source ↗Scholar ↗
2020

Learning the Spatio-Temporal Dynamics of Physical Processes from Partial Observations

Ibrahim Ayed, Emmanuel de Bézenac, Arthur Pajot, Patrick Gallinari
ICASSP 2020accepted

We consider the problem of automatically learning the dynamics of physical processes evolving in space and time from incomplete observations. This is a central problem in many fields that remains complicated for large observation spaces and complex dynamics. We propose a data-driven framework, where…

Cited by 0Source ↗Scholar ↗
2020

Normalizing Kalman Filters for Multivariate Time Series Analysis

Emmanuel de Bézenac, Syama Sundar Rangapuram, Konstantinos Benidis, Michael Bohlke-Schneider, Richard Kurle, Lorenzo Stella +3
NeurIPS 2020poster

This paper tackles the modelling of large, complex and multivariate time series panels in a probabilistic setting. To this extent, we present a novel approach reconciling classical state space models with deep learning methods. By augmenting state space models with normalizing flows, we mitigate imp…

Cited by 155Source ↗PDF ↗Scholar ↗
2020

Stochastic Latent Residual Video Prediction

Jean-Yves Franceschi, Edouard Delasalles, Mickael Chen, Sylvain Lamprier, Patrick Gallinari
ICML 2020poster

Designing video prediction models that account for the inherent uncertainty of the future is challenging. Most works in the literature are based on stochastic image-autoregressive recurrent networks, which raises several performance and applicability issues. An alternative is to use fully latent tem…

Cited by 189Source ↗PDF ↗code ↗Scholar ↗
2019

Context-Aware Zero-Shot Learning for Object Recognition

Eloi Zablocki, Patrick Bordes, Laure Soulier, Benjamin Piwowarski, Patrick Gallinari
ICML 2019oral

Zero-Shot Learning (ZSL) aims at classifying unlabeled objects by leveraging auxiliary knowledge, such as semantic representations. A limitation of previous approaches is that only intrinsic properties of objects, e.g. their visual appearance, are taken into account while their context, e.g. the sur…

Cited by 43Source ↗PDF ↗Scholar ↗
2018

Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge

Emmanuel de Bezenac, Arthur Pajot, Patrick Gallinari
ICLR 2018poster

We consider the use of Deep Learning methods for modeling complex phenomena like those occurring in natural physical processes. With the large amount of data gathered on these phenomena the data intensive paradigm could begin to challenge more traditional approaches elaborated over the years in fie…

Cited by 412Source ↗PDF ↗code ↗Scholar ↗