Publications associées à AdaNCA: Neural Cellular Automata as Adaptors for More Robust Vision Transformer

Publications associées (18)

Deep Neural Networks: Large-Width Behavior and Generalization Bounds

During several decades, neural network architectures have undergone considerable evolution: from shallow to deep, from fully connected to structured (e.g. convolutional, recurrent, or residual), from unnormalized to normalized. The present thesis contribut ...

EPFL2025

Source-Free Domain-Invariant Performance Prediction

Mathieu Salzmann

Accurately estimating model performance poses a significant challenge, particularly in scenarios where the source and target domains follow different data distributions. Most existing performance prediction methods heavily rely on the source data in their ...

Springer Nature2025

Metacognition meets AI: Empowering reflective writing with large language models

Tanja Christina Käser Jacober, Paola Mejia Domenzain, Seyed Parsa Neshaei

Reflective writing is known as a useful method in learning sciences to improve the metacognitive skills of students. However, students struggle to structure their reflections properly, limiting the possible learning gains. Previous works in educational tec ...

Wiley2025

Reweighting simulated events using machine-learning techniques in the CMS experiment

Jan Steggemann, Konstantin Androsov, Anna Mascellani, Joanna Malgorzata Wanczyk, Paul Théodore Gabriel Pablo De Bryas Dexmiers d'Archiac

Data analyses in particle physics rely on an accurate simulation of particle collisions and a detailed simulation of detector effects to extract physics knowledge from the recorded data. Event generators together with a geant-based simulation of the detect ...

2025

Adversarial Training for Jamming-Robust Channel Estimation in OFDM Systems

Pascal Frossard, Javier Alejandro Maroto Morales

Orthogonal frequency-division multiplexing (OFDM) is widely used to mitigate inter-symbol interference (ISI) from multipath fading. However, the open nature of wireless OFDM systems makes them vulnerable to jamming attacks. In this context, pilot jamming i ...

2024

Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning

Devis Tuia, Marc Conrad Russwurm, Thiên-Anh Claris Nguyen, Gaston Jean Lenczner

Monitoring forests, in particular their response to climate and land use change, requires studying long time scales. While efficient deep learning methods have been developed to process short time series of satellite imagery, leveraging long time series of ...

Elsevier Science Inc2024

Federated learning with uncertainty-based client clustering for fleet-wide fault diagnosis

Olga Fink, Hao Lu

Operators from various industries have been pushing the adoption of wireless sensing nodes for industrial monitoring, and such efforts have produced sizeable condition monitoring datasets that can be used to build diagnosis algorithms capable of warning ma ...

2024

One-Bit Byzantine-Tolerant Distributed Learning via Over-The-Air Computation

Yuning Jiang

Distributed learning has become a promising computational parallelism paradigm that enables a wide scope of intelligent applications from the Internet of Things (IoT) to autonomous driving and the healthcare industry. This paper studies distributed learnin ...

2024

Designed Semiconductor Network Random Lasers

Kirsten Emilie Moselund, Alexis Arnaudon

Conventional lasers typically support a well‐defined comb of modes. Coupling many resonators together to form larger complex cavities enables the design of the spatial and spectral distribution of modes, for sensitive and controllable on‐chip light sources ...

Wiley2024

Physics-Informed Machine Learning for Modeling and Control of Dynamical Systems

Colin Neil Jones, Melanie Nicole Zeilinger, Roland Schwan, Xuan Truong Nghiem

Physics-informed machine learning (PIML) is a set of methods and tools that systematically integrate machine learning (ML) algorithms with physical constraints and abstract mathematical models developed in scientific and engineering domains. As opposed to ...

IEEE2023

TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation

Jean-Philippe Thiran, Seyedbehzad Bozorgtabar, Guillaume Marc Georges Vray, Devavrat Tomar

Most recent test-time adaptation methods focus on only classification tasks, use specialized network architectures, destroy model calibration or rely on lightweight information from the source domain. To tackle these issues, this paper proposes a novel Tes ...

Los Alamitos2023

Forest Drought Impact Prediction based on Spatio-temporal Satellite Imagery and Weather Forecasts -- A Spatio-Temporal Approach using Convolutional LSTM Models

Devis Tuia

2023

Bayes-optimal Learning of Deep Random Networks of Extensive-width

Lenka Zdeborová, Florent Gérard Krzakala, Hugo Chao Cui

We consider the problem of learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights. We consider the asymptotic limit where the number of samples, the input dimension and the network width ...

2023

Learning of physical systems: from inference to control

Babak Rahmani

To characterize a physical system to behave as desired, either its underlying governing rules must be known a priori or the system itself be accurately measured. The complexity of full measurements of the system scales with its size. When exposed to real-w ...

EPFL2022

Predicting chemical hazard across taxa through machine learning

Kristin Schirmer, Julita Maria Stadnicka-Michalak

We applied machine learning methods to predict chemical hazards focusing on fish acute toxicity across taxa. We analyzed the relevance of taxonomy and experimental setup, showing that taking them into account can lead to considerable improvements in the cl ...

PERGAMON-ELSEVIER SCIENCE LTD2022

Predictive Analysis of Errors During Robot-Mediated Gamified Training

Pierre Dillenbourg, Arzu Güneysu Özgür

This paper presents our approach to predicting future error-related events in a robot-mediated gamified phys- ical training activity for stroke patients. The ability to predict future error under such conditions suggests the existence of distinguishable fe ...

IEEE2022

Contrastive Learning Inverts the Data Generating Process

Steffen Schneider

Contrastive learning has recently seen tremendous success in self-supervised learning. So far, however, it is largely unclear why the learned representations generalize so effectively to a large variety of downstream tasks. We here prove that feed-forward ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2021

On Block Prediction For Learning-Based Point Cloud Compression

Touradj Ebrahimi, Evangelos Alexiou, Davi Nachtigall Lazzarotto

Point clouds are among popular visual representations for immersive media. However, the vast amount of information generated during their acquisition requires effective compression for practical applications. Although relevant activities from standardizati ...

IEEE2021